FreeTier Agent API MCP server
dev.pages.freetier-agent-api/freetier-agent-apifreetier-agent-api.pages.devstreamable-httpv3.5.0Scanned
x402 or card pay-per-call: invoice JSON, DNS, whois, SSL, geocode, RSS feeds, sitemaps, QR codes
74 tools: 4 do something that can't be undone, 64 change things and 6 only read.
- Reads private data · 0
- Reads text others write · 70
- Can send data out · 15
- 6 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the FreeTier Agent API MCP server can do
The FreeTier Agent API MCP server is published by freetier-agent-api.pages.dev, a domain the MCP Registry verified. It has 74 tools. It can do things that cannot be undone, such as sending, paying or publishing (invoice_json, currency, translate and pack_payment_verification) and create or change data (64 tools: mcp_servers_sample, llm_pricing_sample, api_directory_sample, token_risk and 60 more), but cannot delete data. 6 tools only read.
70 tools bring in text other people can write (invoice_json, token_risk, tx_explain and 67 more); 15 tools can send data out of your system (invoice_json, site_contacts, page_rag and 12 more).
The fixed checks matched 6 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 5 times since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 3.5.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
74 tools
Can't be undone 4Claude Code: ask
currency3 free MCP calls per day (all tools together), then $0.002 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "currency" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.002 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Currency conversion with official ECB euro reference rates (~30 currencies, daily). Params: from, to, amount. Also returns the rate date. When to use: Use currency for ECB reference exchange rates and conversion.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
invoice_jsonSend exactly one of url, text, or file_base64 + mime_type.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "invoice_json" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
Description, as the server wrote it Send exactly one of url, text, or file_base64 + mime_type. 3 free MCP calls per day (all tools together), then $0.0075 USDC per page via x402 or card credits (paid in-band: params._meta["x402/payment"]). Invoice or receipt (PDF, PNG/JPEG/WebP image, or plain text) to structured JSON with a fixed schema: vendor (name, address, VAT ID, email, phone, IBAN), customer, invoice number, order number, issue/due date, currency (ISO 4217), subtotal, VAT total, total, amount due, VAT breakdown and line items. Every field has value, the verbatim source quote and a confidence score (0-1: quote found in the document, value matches quote, totals add up). Arithmetic checks included. $0.0075 per page (max 10 pages per call; the 402 quotes pages x $0.0075), 1 free call per caller (up to 3 pages). Runs on Cloudflare Workers AI only (PDF text layer via toMarkdown, OCR for images); documents are not stored. Scanned PDFs without a text layer: send page images. POST JSON {url} or {file_base64, mime_type} or {text}, or POST the raw file (Content-Type application/pdf or image/*); GET ?url= or ?text= also works. When to use: Use invoice-json for invoices and receipts (fixed accounting schema, quotes, arithmetic checks). Use extract-json for any other short text with your own JSON schema. Use page-rag to turn a web page into Markdown for retrieval. Pay by card instead of crypto: put a Gumroad license key from https://freetier.gumroad.com/l/gvyfk in params._meta["x-license-key"] (or HTTP header X-License-Key); 7.5 credits ($0.0075) per page, rounded down per call. Time limit about 22 s per call; on timeout or error nothing is charged or settled.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
pack_payment_verification3 free MCP calls per day (all tools together), then $0.008 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others write1 finding
Why it is in this group
- The name "pack_payment_verification" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "pack_payment_verification" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "pack_payment_verification" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.008 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). FreeTier Payment Verification pack: Verify a blockchain transaction before you trust it: live status (confirmed, pending or failed) plus a plain-language explanation of what the transaction actually did. One call for agents that handle payments. Info: https://freetier-agent-api.pages.dev/packs/payment-verification
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
translate3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "translate" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Text translation: translate up to 3,000 characters into one of 28 languages (en, da, de, fr, es, it, pt, nl, sv, no, fi, pl, ru, uk, tr, ar, hi, ja, ko, zh, id, vi, th, cs, ro, el, he, hu), source auto-detected. Small LLM (Workers AI). GET query or POST JSON body. When to use: Use translate for short texts into 28 languages.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Changes things 64Claude Code: ask
agent_tools3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Agent tools search: One search across ~13,000 agent tools: 4,259 MCP servers (awesome-mcp-servers, MIT) and ~8,900 x402 pay-per-call APIs (nohumans.directory, CC BY 4.0). Filters: q, type=mcp|x402, limit<=100.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
api_directory_sampleFree.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Free. Five live public APIs that need no key.
base_gas3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Base gas price: Live Base mainnet gas price (gwei), latest block, and estimated ETH cost of a USDC transfer (~65k gas) and a plain ETH transfer (21k gas). When to use: Use base-gas for current Base gas price and the cost of a transfer.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
classify3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Text classification: classify text (max 6,000 chars) into your own labels (2-20, single or multi-label) with confidence and a short reason; output is always one of your labels. Small LLM (Workers AI Llama 3.1 8B). GET query or POST JSON body. When to use: Use classify to route tickets, emails or posts into your own labels.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
company_batch3 free MCP calls per day (all tools together), then $0.022 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.022 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Company enrichment batch: up to 10 domains in one call, each with profile (name, description, socials, key pages, email provider) and detected tech stack. Only each company's own website and DNS; no personal data. When to use: Use company-batch to enrich a list of up to 10 domains in one call.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
company_contacts3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Company contacts: public business contact details from the company's own website only - role emails (info@, sales@) with MX check, main phone numbers (E.164), address, company/VAT ids and official social profiles. Personal emails and names omitted (GDPR). robots.txt respected. When to use: Use company-contacts for public role emails and main phone of a company domain (no personal data).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
company_profile3 free MCP calls per day (all tools together), then $0.0075 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0075 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Company enrichment: domain in, company profile out - name, description, language, logo, founding date, address (schema.org), official social profiles, key pages (contact, about, careers, pricing) and email provider (MX). Only the company's own website and DNS; robots.txt respected; no personal data. When to use: Use company-profile to enrich a domain; company-techstack for technologies; company-contacts for business contact details; company-batch for up to 10 domains.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
company_techstack3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Website tech stack detection: CMS, e-commerce, frameworks, analytics, marketing, support chat, payments, consent, CDN/hosting and email provider used by a company website, each with evidence (HTML, header or DNS). ~70 signatures. When to use: Use company-techstack to see which CMS, analytics, chat and payment tools a website uses.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contract_abi3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Base or Ethereum contract address -> ABI and function list: Sourcify verification (exact/partial match), contract name, compiler, ABI, function selectors + signatures, event topics; proxies (EIP-1967, ZeppelinOS, others Sourcify detects) resolved to the implementation with its own ABI. Unverified contracts: selectors guessed from bytecode and named via the public OpenChain database. abi=false returns signatures only (smaller). When to use: Use contract-abi when an agent needs to call or decode a contract it has not seen before. Use wallet-profile for balances and account type, and token-risk to check an ERC-20 for dangerous privileges.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
country3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Country reference lookup by ISO2/ISO3/name: capital, population, area, continent, currency, phone prefix, TLD, languages, neighbours, time zones with current UTC offset and local time. When to use: Use country for ISO codes, capitals, currencies, calling codes and time zones.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
dataset_fullDataset download: $1 USDC via x402.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Dataset download: $1 USDC via x402. Buy the full Verified API Directory dataset (2,230 rows, JSON, CC BY 4.0 + MIT sources) in one call.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
dns3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). DNS lookup over DNS-over-HTTPS (Cloudflare, Google fallback): A, AAAA, MX, NS, TXT, CNAME, CAA, SOA, SRV, HTTPS, DS... for one domain in one call, plus a mail-auth check (MX hosts, SPF, DMARC policy, warnings) and the DNSSEC-validated flag. When to use: Use dns to read any DNS records of a domain and check its mail setup (MX, SPF, DMARC) in one call. Use email-verify to check a single address.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
domain_whois3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Domain registration lookup via RDAP (the official whois successor, IANA bootstrap): registered or not, registrar + IANA id + abuse email, created / updated / expiry dates, days to expiry, domain age, EPP status codes, nameservers, DNSSEC. Use it to vet a domain or check expiry. When to use: Use domain-whois to see who registered a domain, when it was created and when it expires (RDAP, official registry data).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
dump_agent_toolsDataset download: $1 USDC via x402.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Dataset download: $1 USDC via x402. Full dump: Agent Tool Directory, ~13,000 MCP servers + x402 APIs in one unified schema (JSON). MIT + CC BY 4.0 sources, attribution included.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
dump_llm_pricingDataset download: $1 USDC via x402.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Dataset download: $1 USDC via x402. Full dump: list prices of ~3,000 AI models (LiteLLM table, MIT) + verified AI/dev free tiers with limits (JSON).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
dump_mcp_serversDataset download: $1 USDC via x402.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Dataset download: $1 USDC via x402. Full MCP server directory dump (4,259 servers, JSON). Source awesome-mcp-servers (MIT).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
dump_world_referenceDataset download: $1 USDC via x402.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Dataset download: $1 USDC via x402. Full dump: 252 countries (GeoNames, CC BY 4.0), 418 time zones, ~14,000 public holidays 2026-2027 (python-holidays, MIT). JSON.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
dump_x402_servicesDataset download: $1 USDC via x402.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Dataset download: $1 USDC via x402. Full dump: ~8,900 x402 pay-per-call APIs with category, price, chains and probe status (JSON). Data from nohumans.directory, CC BY 4.0, attribution required.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
email_verify3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Email verify: Email address check WITHOUT sending mail or SMTP probing: RFC-style syntax check, domain MX/A records via DNS-over-HTTPS, disposable-domain flag (CC0 blocklist, ~9,900 domains), role-address flag (info@, support@...), free-mail flag. Verdict: deliverable_domain | risky | invalid. Cannot confirm that the mailbox itself exists. Addresses are not stored or logged. When to use: Use email-verify to check syntax, MX and disposable domains for one address (DNS only, no mailbox probe).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
email_verify_batch3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Email verification batch: up to 20 email addresses in one call - syntax, MX/A records via DNS-over-HTTPS, null MX, disposable, role and free-mail flags, verdict per address and a summary. No SMTP probing, nothing stored. When to use: Use email-verify-batch to clean a list of up to 20 emails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
email_verify_quick3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Email quick check: offline syntax check, disposable-domain flag (~9,900 domains), role address and free-mail flags for one email, no DNS (fastest). Use email-verify for MX checks. When to use: Use email-verify-quick for a fast offline syntax/disposable check; email-verify adds MX; email-verify-batch for lists.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
ens3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). ENS + Basenames resolver: name -> address (vitalik.eth, jesse.base.eth) or address -> verified primary name on Ethereum and Base (reverse record checked forward), plus optional text records (avatar, url, com.twitter, com.github, ...). On-chain via public RPC, no keys. When to use: Use ens to turn vitalik.eth / name.base.eth into an address before sending, or to show a verified name for an address.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
entity_extract3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Named entity extraction: people, organizations, locations, dates, money amounts and products from text (max 6,000 chars), plus emails and URLs by regex. Every AI entity is checked to literally occur in the text. GET query or POST JSON body. When to use: Use entity-extract for people, companies, places, dates and amounts; extract-json when you need your own schema.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
extract_json3 free MCP calls per day (all tools together), then $0.01 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.01 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Extract JSON: Messy text + JSON Schema in, clean JSON out. Uses a small LLM (Cloudflare Workers AI, Llama 3.1 8B, JSON mode) when available, else a deterministic key:value/regex extractor; the result is type-checked against your schema and missing fields are null. Limits: text <= 6,000 chars, schema <= 30 top-level properties (flat objects, arrays of scalars); the model can misread ambiguous text, so check important values. Params: text, schema (JSON string), mode=auto|heuristic. GET query or POST JSON body. When to use: Use extract-json for short free text with your own JSON schema; for invoices and receipts use invoice-json.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
feed_json3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). RSS / Atom / JSON Feed to clean JSON: give a feed URL (or a web page that links one, auto-discovered) and get feed title/link/language plus normalised items: id, title, link, ISO dates, author, plain-text summary, categories, enclosures (podcast audio, media), image. Filter with since= and limit=; include_content=true adds the full text. When to use: Use feed-json to read an RSS/Atom/JSON feed (or find the feed of a site) as clean JSON items, e.g. to watch a blog, changelog, podcast or news source. Use page-rag for the full text of one article page.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
free_tiers3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Free tiers: Current free-tier limits for developer services (hosting, DB, auth, email, CI, monitoring) and AI/LLM APIs, with official source URLs. Filter: q, category.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
gas3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Gas price (5 EVM chains): Live gas prices across 5 EVM chains in one call (Ethereum, Base, Arbitrum, Optimism, Polygon): gas price in gwei, latest block, and the cost of an ETH transfer, an ERC-20/USDC transfer and a swap in native coin and USD, plus a ranking of which chain is cheapest right now. Public RPC nodes with failover; no keys. When to use: Use gas to pick the cheapest EVM chain right now or to price a transfer/swap on Ethereum, Base, Arbitrum, Optimism or Polygon in one call. Use base-gas for Base only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
geocode3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Geocoding with OpenStreetMap Nominatim: address or place name -> coordinates (up to 5 matches, optional country filter), or lat+lon -> structured address (reverse). Structured address fields, country code, bounding box, OSM id. Cached; ODbL attribution included. When to use: Use geocode to turn an address or place into coordinates, or coordinates into an address (OpenStreetMap).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
geocode_batch3 free MCP calls per day (all tools together), then $0.002 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.002 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Geocode batch: up to 5 addresses or place names (separated by |) to coordinates and a structured address in one call, optional country filter. OpenStreetMap Nominatim, cached, ODbL attribution. When to use: Use geocode-batch for up to 5 addresses at once.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
holidays3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Public holidays for ~490 countries/territories for 2026 and 2027; optional date=YYYY-MM-DD answers is_holiday. When to use: Use holidays to list public holidays or test one date for a country.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
link_check3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data out1 finding
Why it is in this group
- The name "link_check" says "link": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "link_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "link_check" says "link": a word for a change.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Check up to 20 URLs in one call: HTTP status, final URL after redirects, redirect count, latency, content-type, ok flag. When to use: Use link-check to test up to 20 URLs for broken links in one call.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
llm_cost3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token & cost calculator: estimate tokens for a text (or pass input_tokens/output_tokens) and price it across several models using provider list prices (LiteLLM price table, MIT). Params: models (comma list of model ids like gpt-4o-mini, claude-sonnet-4-5, gemini/gemini-2.5-flash or search words, max 15), text or input_tokens, output_tokens, calls. When to use: Use llm-cost to compare what a workload costs across models.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
llm_pricing3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). LLM pricing: AI model list prices (USD per 1M input/output/cached tokens, context window, vision/tools/reasoning flags) for ~3,000 models across OpenAI, Anthropic, Google, Mistral, Groq, Bedrock, Azure, Together, Fireworks and more, plus verified free tiers/rate limits of AI APIs. Filters: q, provider, free=yes, max_input_per_m, min_context, vision=yes, tools=yes, sort=input|output|context, limit<=100.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
llm_pricing_sampleFree.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Free. List prices of five popular LLMs (USD per 1M tokens, LiteLLM table, MIT).
mcp_servers3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). MCP servers search: Search 4,259 MCP (Model Context Protocol) servers by keyword, category, language (python/typescript/go/rust...), scope (cloud/local) and official flag. Returns repo URL and description.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
mcp_servers_sampleFree.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Free. Five sample MCP servers from the 4,259-server directory (MIT source).
news_entity3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Entity news last 24h: who is writing about a company, person or project in the last 24 hours - article count, top sources, top countries, headlines - plus a Wikipedia identity check of the entity. Data: GDELT DOC 2.0 + Wikipedia. When to use: Use news-entity for a 24h media snapshot of one company, person or project.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
news_monitor3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). News search and monitor: latest news articles worldwide (65+ languages) matching keywords in a time window (1h to 2 weeks), newest first, with title, URL, source domain, language, country and time. Data: GDELT Project DOC 2.0 API. When to use: Use news-monitor to fetch the latest articles for keywords; news-entity for a 24h who-writes-about-X digest; news-sentiment for tone.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
news_sentiment3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). News sentiment: average tone of worldwide news coverage about a topic, company or person over a window (default 7 days) with label (negative to positive), trend (improving/worsening/stable) and the tone timeline. Data: GDELT DOC 2.0 tone analysis. When to use: Use news-sentiment to judge whether coverage of a topic is negative or positive, and its trend.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
pack_ai_tool_discovery3 free MCP calls per day (all tools together), then $0.012 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.012 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). FreeTier AI Tool Discovery pack: Discover AI-agent tooling in one call: matching MCP servers, x402 pay-per-call services and agent tools for any query. Built for agents that need to find and chain new capabilities at runtime. Info: https://freetier-agent-api.pages.dev/packs/ai-tool-discovery
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
pack_b2b_lead_finder3 free MCP calls per day (all tools together), then $0.022 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.022 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). FreeTier B2B Lead Finder pack: Find B2B leads on any company website in one call: contact emails and people from the site, a company profile, its tech stack, and quick deliverability verification of up to 3 emails found. Output is ready for outreach tooling. Info: https://freetier-agent-api.pages.dev/packs/b2b-lead-finder
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
pack_domain_health3 free MCP calls per day (all tools together), then $0.025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). FreeTier Domain Health Check pack: Full health check for a domain in one call: WHOIS ownership and expiry, DNS records, SSL certificate status, robots.txt rules and sitemap availability. Use it to vet a site before outreach, purchases or integrations. Info: https://freetier-agent-api.pages.dev/packs/domain-health
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
pack_wallet_safety3 free MCP calls per day (all tools together), then $0.024 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.024 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). FreeTier Wallet Safety Scan pack: Full safety scan of any wallet before you transact: profile and holdings, portfolio value, per-token risk scoring and a rug-pull check, combined into one verdict (low, medium or high risk). One call instead of four, built for AI agents on x402. Info: https://freetier-agent-api.pages.dev/packs/wallet-safety
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
pack_website_to_rag3 free MCP calls per day (all tools together), then $0.015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). FreeTier Website to RAG pack: Turn any web page into clean AI-ready data in one call: the page as markdown, a RAG-ready index for retrieval, and page metadata (title, description). Built for agents that need to read, quote and answer from a URL. Info: https://freetier-agent-api.pages.dev/packs/website-to-rag
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
page_check3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). One-call page audit for agents: HTTP status, redirects, latency, title, meta description, canonical, lang, Open Graph, JSON-LD types, headings, word count, plus agent-friendliness: robots.txt rules for 14 AI crawlers, llms.txt, sitemap, and a 0-100 score with reasons. When to use: Use page-check for status, redirects, headers and SEO basics of a URL; for content use page-rag.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
page_markdown3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Page to Markdown: Convert a public web page to clean Markdown (title, headings, paragraphs, lists, links, code), scripts/nav/footer removed, max ~60k chars. robots.txt respected. When to use: Legacy converter. page-rag gives cleaner main-content Markdown plus chunks at the same price.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
page_meta3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Fetch a public web page (robots.txt respected) and return title, meta description, canonical, Open Graph/Twitter tags, language, headings, link counts, HTTP status. When to use: Use page-meta for title, description, Open Graph and headings only; for full content use page-rag.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
page_rag3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Page RAG: Any public web page -> clean LLM-ready Markdown + RAG chunks in one call: main content via Mozilla Readability (no nav/ads/footers), absolute links, title/description/language/canonical/published+modified dates/JSON-LD types, word + token estimates, sha256 content hash for change detection, and heading-aware chunks (configurable size + overlap, each with its heading path). Plain HTTP, robots.txt respected, Markdown/plain text passed through. Flags pages that likely need JavaScript. When to use: Use page-rag to feed a web page into an LLM or a vector store. Use page-meta or page-check for SEO/meta tags and HTTP status only. page-markdown is the older, simpler converter; page-rag is recommended.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
qr_code3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...(e.g. ethereum:/USDC request) or Wi-Fi credentials (ssid + password) to a QR code as SVG (..."
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). QR code generator: text, URL, payment URI (e.g. ethereum:/USDC request) or Wi-Fi credentials (ssid + password) to a QR code as SVG (inline + data URI) and/or GIF data URI. Error correction L/M/Q/H, scale, quiet-zone margin, colours, optional 0/1 module matrix. UTF-8 byte mode, computed locally, nothing stored. When to use: Use qr-code to turn a URL, payment request, Wi-Fi login or any text into a scannable QR image (SVG or GIF data URI).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
robots_check3 free MCP calls per day (all tools together), then $0.003 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.003 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Check whether a URL may be crawled per the site's robots.txt for a given user-agent. Returns allowed, matched rule, crawl-delay, sitemaps. When to use: Use robots-check before crawling a URL with your own user-agent.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
rug_check3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Rug pull check: one ERC-20 token, pass/warn/fail on four groups - honeypot signals (GoPlus simulation, buy/sell tax, cannot sell all), owner rights (mint, blacklist, pause, hidden owner, proxy, renounce, source verified), liquidity (USD, pairs, pair age, LP locked/burned) and holder concentration - plus an overall rugRisk. Base or Ethereum. Data: GoPlus Security public API (contract flags, taxes, honeypot simulation, holders, LP lock) + DexScreener (pairs, liquidity, volume). Every flag names its source field. Not financial advice. When to use: Use rug-check for new or unknown tokens (memecoins, snipes): honeypot, owner rights, liquidity and holder checks with pass/warn/fail.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
site_contacts3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Site contacts: Company website -> one clean contact row: role emails only (info@, sales@ ...) with MX check, phones validated and normalized to E.164 with confidence, schema.org address/name, Danish CVR and EU VAT ids, official social profiles. Respects robots.txt, plain HTTP, home + up to 5 contact pages. Personal emails omitted (GDPR). When to use: Use site-contacts when you need the business contact details of a company from its own website. Use page-rag when you need the text of a page, and email-verify to check one email address you already have.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
sitemap3 free MCP calls per day (all tools together), then $0.003 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.003 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Sitemap to URL list: give a sitemap URL or just a domain (sitemaps found via robots.txt, then /sitemap.xml). Follows sitemap indexes (newest first, up to 10 child sitemaps), reads .xml, .xml.gz and text sitemaps, and returns every URL with lastmod, changefreq, priority, hreflang alternates, image and news counts. Filter by contains= and since= (lastmod). When to use: Use sitemap to list all pages a site declares (with lastmod) before crawling or to find recently changed pages. Use robots-check for crawl permission of one URL.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
ssl_cert3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). TLS/SSL certificate check from public Certificate Transparency logs (Cert Spotter, crt.sh fallback): currently valid certificates for a hostname, newest first, with issuer, validity dates, days left, SAN names and an expiring-within-14-days flag. For expiry monitoring and phishing/subdomain vetting. When to use: Use ssl-cert to check TLS certificate expiry and issuer for a hostname from public CT logs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_info3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). ERC-20 token lookup on Ethereum, Base, Arbitrum, Optimism or Polygon: name, symbol, decimals, total supply (raw + human), live USD price with confidence (DefiLlama) and FDV, for up to 10 token addresses in one call. Use it before showing, pricing or converting a token amount. When to use: Use token-info before displaying, converting or pricing an ERC-20 amount: decimals, symbol, supply and USD price for up to 10 tokens in one call.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_portfolio3 free MCP calls per day (all tools together), then $0.01 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.01 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token portfolio risk scan: up to 20 ERC-20 tokens in one call, each with risk level, score, top flags, liquidity and price, plus a summary (count per risk level, average score, riskiest tokens). Base or Ethereum. Data: GoPlus Security public API (contract flags, taxes, honeypot simulation, holders, LP lock) + DexScreener (pairs, liquidity, volume). Every flag names its source field. Not financial advice. When to use: Use token-portfolio to risk-rank up to 20 holdings of a wallet in one call.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_price3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token price: current USD price of one token by contract address from DEX data, plus market cap, FDV, 24h volume, liquidity and 24h change. Base, Ethereum, Solana, Arbitrum, BSC, Polygon, Optimism, Avalanche. Data: GeckoTerminal public DEX API (prices, pools, OHLCV across 8 chains). Not financial advice. When to use: Use token-price for one token, token-prices for up to 30 at once, token-price-history for candles, token-pools for liquidity.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_price_history3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token price history: OHLCV candles (daily up to 180, hourly up to 168) for one token from its most liquid DEX pool, with period change, high and low. Data: GeckoTerminal public DEX API (prices, pools, OHLCV across 8 chains). Not financial advice. When to use: Use token-price-history for daily or hourly OHLCV candles of a DEX token.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_prices3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token prices (multi): USD prices for up to 30 tokens on one network in one call, with market cap, 24h volume and 24h change per token. Data: GeckoTerminal public DEX API (prices, pools, OHLCV across 8 chains). Not financial advice. When to use: Use token-prices to price a whole portfolio or watchlist in one call.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_risk3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token risk: Deterministic ERC-20 risk check on Base or Ethereum from public on-chain data only: privileged functions in bytecode (mint, blacklist, pause, fees, limits, trading switch), upgradeable proxy + implementation, owner and renounce status, Uniswap v2/v3 + Aerodrome liquidity in USD (Chainlink), owner/pool/burned supply share. Every flag has evidence; lists what was NOT checked (no honeypot simulation). Not financial advice. When to use: Use token-risk before an agent buys, lists or recommends an ERC-20 token. It reads public chain data only: it does not simulate buys/sells (no honeypot test) and does not return price history or market data.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_score3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token risk score: one ERC-20 token scored (0-100) with a short AI verdict (Workers AI rephrasing only the computed facts; rule-based fallback), risk level, evidence flags, taxes, holder concentration, owner status and DEX liquidity. Base or Ethereum. Data: GoPlus Security public API (contract flags, taxes, honeypot simulation, holders, LP lock) + DexScreener (pairs, liquidity, volume). Every flag names its source field. Not financial advice. When to use: Use token-score for a quick risk score + AI verdict on one token before a trade. Use rug-check for a pass/fail breakdown, token-compare to pick between two, token-portfolio for up to 20 tokens, token-risk for our own on-chain bytecode analysis.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
wallet_profile3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Base or Ethereum address -> profile in one call: EOA, contract or EIP-7702-delegated EOA; ETH balance; nonce (tx count); balances of major tokens (USDC, USDT, EURC, DAI, WETH, cbBTC/WBTC, USDbC); for contracts: bytecode size, EIP-1967/ZeppelinOS proxy implementation, beacon, owner(), ERC-20 name/symbol/decimals/supply and Sourcify verification. Public RPC data only. When to use: Use wallet-profile before sending funds to or trusting an address (is it a contract? does it hold USDC?). Use tx-explain for one transaction and contract-abi for the full interface of a contract.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
wiki_fact3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.005 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Wikipedia fact lookup: best-matching Wikipedia article for a query with summary, description, URL and structured Wikidata facts (type, country, headquarters, founded, founders, CEO, website, industry, employees, ticker, population, coordinates). Any Wikipedia language. When to use: Use wiki-fact to ground an entity: summary plus structured facts (founded, HQ, CEO, website).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
x402_services3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). x402 services search: Search ~8,900 live x402 pay-per-call APIs (verified/unverified by nohumans.directory probes, CC BY 4.0): name, endpoint URL, category, price, chains, status, score. Filters: q, category, chain, max_price, status=verified, limit<=100.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Only reads 6Show 6 read-only tools
apis_search3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- The name "apis_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.001 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). API search: Search 2,230 link-checked public & free-tier APIs (59 categories). Filters: q, category, auth=none, alive=yes, https=yes, kind, limit<=50.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
list_endpointsFree.No findings
Why it is in this group
- The name "list_endpoints" says "list": a word for reading.
Description, as the server wrote it Free. List every endpoint (core products first) with its price in USDC, description and example query. Core: invoice-json $0.0075/page, token-risk $0.005, tx-explain $0.0025, wallet-profile $0.005, contract-abi $0.0025, site-contacts $0.004, page-rag $0.0025, token-info $0.0025, ens $0.0025, tx-status $0.0015, dns $0.0025, domain-whois $0.005, ssl-cert $0.005, geocode $0.0015; utilities $0.001-$0.01; dataset downloads $1. 1 free call per route per caller.
summarize3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- The name "summarize" says "summarize": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.004 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Text summarizer: summarize up to 12,000 characters into 3-6 bullet points or one paragraph (max_words 20-250, optional output language). Small LLM (Workers AI Llama 3.1 8B), facts only from the text. GET query or POST JSON body. When to use: Use summarize to condense long text into bullets or a paragraph.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_compare3 free MCP calls per day (all tools together), then $0.0075 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- The name "token_compare" says "compare": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0075 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Token risk comparison: two ERC-20 tokens side by side: which has the lower risk score and why, flags only one of them has, taxes, holders, liquidity, volume, plus a short AI verdict from the computed facts (rule-based fallback). Base or Ethereum. Data: GoPlus Security public API (contract flags, taxes, honeypot simulation, holders, LP lock) + DexScreener (pairs, liquidity, volume). Every flag names its source field. Not financial advice. When to use: Use token-compare when an agent must choose between two tokens.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
tx_explain3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- The name "tx_explain" says "explain": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0025 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Base or Ethereum transaction hash -> plain JSON: status (success/failed/pending), block time, confirmations, from/to, ETH value, gas used and fee (incl. Base L1 fee), method selector + name, and every ERC-20/ERC-721 Transfer in the receipt with token symbol, decimals and human amounts. Optional payment check: expect_to + expect_token (USDC, ETH, symbol or address) + expect_amount confirms a payment arrived (e.g. verify a USDC or x402 settlement). Public RPC data only. When to use: Use tx-explain to understand one transaction or to verify a payment (USDC, ETH, any ERC-20) before delivering goods. Use wallet-profile for an address, contract-abi for a contract interface and token-risk to judge a token.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
tx_status3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]).Reads text others writeNo findings
Why it is in this group
- The name "tx_status" says "status": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3 free MCP calls per day (all tools together), then $0.0015 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Transaction status for polling: up to 10 tx hashes in one call, searched across Ethereum, Base, Arbitrum, Optimism and Polygon (or one chain): pending / success / failed / not_found, block, confirmations, finalized flag, from/to, gas used, fee in native coin, explorer link. When to use: Use tx-status to poll whether transactions are pending, confirmed, failed or finalized (up to 10 hashes, chain auto-detected). Use tx-explain for a full decode of one tx.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write70
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out15
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:52 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 68
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 68 tools that change things (4 irreversible, 64 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://freetier-agent-api.pages.dev/mcp: tools/list returned 74 tools to an anonymous client, including invoice_json (irreversible), currency (irreversible), translate (irreversible), pack_payment_verification (irreversible), mcp_servers_sample (write) and 63 more
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 62 to 68
- Oct 29, 2026
- Tools that change things, listed without credentials: 27 to 62
Findings
Matches of fixed checks, with the text they matched.
- Warninvoice_json
The server marks "invoice_json" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
- Warnlink_check
The server marks "link_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "link_check" says "link": a word for a change.
- Warncurrency
The server marks "currency" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
- Warntranslate
The server marks "translate" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
The server marks "pack_payment_verification" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "pack_payment_verification" says "payment": a word that usually means money moves, which cannot be taken back.
- Infoqr_code
The description mentions "credentials".
What this check looks forMatched text
description: "...(e.g. ethereum:/USDC request) or Wi-Fi credentials (ssid + password) to a QR code as SVG (..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools28 added, 37 changed.+28 added~37 changedView diff
- Added:classifyChanges things
- Added:company_batchChanges things
- Added:company_contactsChanges things
- Added:company_profileChanges things
- Added:company_techstackChanges things
- Added:email_verify_batchChanges things
- Added:email_verify_quickChanges things
- Added:entity_extractChanges things
- Added:geocode_batchChanges things
- Added:news_entityChanges things
- Added:news_monitorChanges things
- Added:news_sentimentChanges things
- Added:pack_ai_tool_discoveryChanges things
- Added:pack_b2b_lead_finderChanges things
- Added:pack_domain_healthChanges things
- Added:pack_payment_verificationCan't be undone
- Added:pack_wallet_safetyChanges things
- Added:pack_website_to_ragChanges things
- Added:rug_checkChanges things
- Added:summarizeOnly reads
- Added:token_compareOnly reads
- Added:token_portfolioChanges things
- Added:token_priceChanges things
- Added:token_price_historyChanges things
- Added:token_pricesChanges things
- Added:token_scoreChanges things
- Added:translateCan't be undone
- Added:wiki_factChanges things
- Changed:agent_toolsChanges thingsdescription
- Changed:apis_searchOnly readsdescription
- Changed:base_gasChanges thingsdescription
- Changed:contract_abiChanges thingsdescription
- Changed:countryChanges thingsdescription
- Changed:currencyCan't be undonedescription
- Changed:dnsChanges thingsdescription
- Changed:domain_whoisChanges thingsdescription
- Changed:email_verifyChanges thingsdescription
- Changed:ensChanges thingsdescription
- Changed:extract_jsonChanges thingsdescription
- Changed:feed_jsonChanges thingsdescription
- Changed:free_tiersChanges thingsdescription
- Changed:gasChanges thingsdescription
- Changed:geocodeChanges thingsdescription
- Changed:holidaysChanges thingsdescription
- Changed:invoice_jsonCan't be undonedescription
- Changed:link_checkChanges thingsdescription
- Changed:list_endpointsOnly readsdescription
- Changed:llm_costChanges thingsdescription
- Changed:llm_pricingChanges thingsdescription
- Changed:mcp_serversChanges thingsdescription
- Changed:page_checkChanges thingsdescription
- Changed:page_markdownChanges thingsdescription
- Changed:page_metaChanges thingsdescription
- Changed:page_ragChanges thingsdescription
- Changed:qr_codeChanges thingsdescription
- Changed:robots_checkChanges thingsdescription
- Changed:site_contactsChanges thingsdescription
- Changed:sitemapChanges thingsdescription
- Changed:ssl_certChanges thingsdescription
- Changed:token_infoChanges thingsdescription
- Changed:token_riskChanges thingsdescription
- Changed:tx_explainOnly readsdescription
- Changed:tx_statusOnly readsdescription
- Changed:wallet_profileChanges thingsdescription
- Changed:x402_servicesChanges thingsdescription
PostureRemote posture changed. Tools that change things, listed without credentials: 62 -> 68.View diff
- Tools that change things, listed without credentials: 62 to 68
PostureRemote posture changed. Tools that change things, listed without credentials: 27 -> 62.View diff
- Tools that change things, listed without credentials: 27 to 62
Tools7 added, 4 changed.+7 added~4 changedView diff
- Added:dnsChanges things
- Added:domain_whoisChanges things
- Added:feed_jsonChanges things
- Added:geocodeChanges things
- Added:qr_codeChanges things
- Added:sitemapChanges things
- Added:ssl_certChanges things
- Changed:ensChanges thingstitle
- Changed:list_endpointsOnly readsdescription
- Changed:token_infoChanges thingstitle
- Changed:tx_statusOnly readstitle
Tools3 added, 22 changed.+3 added~22 changedView diff
- Added:ensChanges things
- Added:token_infoChanges things
- Added:tx_statusOnly reads
- Changed:base_gasChanges thingsdescription
- Changed:contract_abiChanges thingsdescription
- Changed:countryChanges thingsdescription
- Changed:currencyCan't be undonedescription
- Changed:email_verifyChanges thingsdescription
- Changed:extract_jsonChanges thingsdescription
- Changed:gasChanges thingsdescription
- Changed:holidaysChanges thingsdescription
- Changed:invoice_jsonCan't be undonedescription
- Changed:link_checkChanges thingsdescription
- Changed:list_endpointsOnly readsdescription
- Changed:llm_costChanges thingsdescription
- Changed:llm_pricingChanges thingsdescription
- Changed:page_checkChanges thingsdescription
- Changed:page_markdownChanges thingsdescription
- Changed:page_metaChanges thingsdescription
- Changed:page_ragChanges thingsdescription
- Changed:robots_checkChanges thingsdescription
- Changed:site_contactsChanges thingsdescription
- Changed:tx_explainOnly readsdescription
- Changed:wallet_profileChanges thingsdescription
- Changed:x402_servicesChanges thingsdescription
Tools4 added, 1 changed.+4 added~1 changedView diff
- Added:contract_abiChanges things
- Added:gasChanges things
- Added:tx_explainOnly reads
- Added:wallet_profileChanges things
- Changed:list_endpointsOnly readsdescription
Tools4 added, 25 changed.+4 added~25 changedView diff
- Added:invoice_jsonCan't be undone
- Added:page_ragChanges things
- Added:site_contactsChanges things
- Added:token_riskChanges things
- Changed:agent_toolsChanges thingstitledescription
- Changed:apis_searchOnly readstitledescription
- Changed:base_gasChanges thingstitledescription
- Changed:countryChanges thingstitledescription
- Changed:currencyCan't be undonetitledescription
- Changed:dataset_fullChanges thingstitledescription
- Changed:dump_agent_toolsChanges thingstitledescription
- Changed:dump_llm_pricingChanges thingstitledescription
- Changed:dump_mcp_serversChanges thingstitledescription
- Changed:dump_world_referenceChanges thingstitledescription
- Changed:dump_x402_servicesChanges thingstitledescription
- Changed:email_verifyChanges thingstitledescription
- Changed:extract_jsonChanges thingstitledescription
- Changed:free_tiersChanges thingstitledescription
- Changed:holidaysChanges thingstitledescription
- Changed:link_checkChanges thingstitledescription
- Changed:list_endpointsOnly readstitledescription
- Changed:llm_costChanges thingstitledescription
- Changed:llm_pricingChanges thingstitledescription
- Changed:mcp_serversChanges thingstitledescription
- Changed:page_checkChanges thingstitledescription
- Changed:page_markdownChanges thingstitledescription
- Changed:page_metaChanges thingstitledescription
- Changed:robots_checkChanges thingstitledescription
- Changed:x402_servicesChanges thingstitledescription
Install
Pinned to version 3.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http freetier-agent-api https://freetier-agent-api.pages.dev/mcpclaude mcp add --transport http freetier-agent-api https://freetier-agent-api.pages.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__freetier-agent-api__list_endpoints",
"mcp__freetier-agent-api__tx_explain",
"mcp__freetier-agent-api__tx_status",
"mcp__freetier-agent-api__apis_search",
"mcp__freetier-agent-api__token_compare",
"mcp__freetier-agent-api__summarize"
],
"ask": [
"mcp__freetier-agent-api__mcp_servers_sample",
"mcp__freetier-agent-api__llm_pricing_sample",
"mcp__freetier-agent-api__api_directory_sample",
"mcp__freetier-agent-api__invoice_json",
"mcp__freetier-agent-api__token_risk",
"mcp__freetier-agent-api__wallet_profile",
"mcp__freetier-agent-api__contract_abi",
"mcp__freetier-agent-api__site_contacts",
"mcp__freetier-agent-api__page_rag",
"mcp__freetier-agent-api__robots_check",
"mcp__freetier-agent-api__page_meta",
"mcp__freetier-agent-api__llm_cost",
"mcp__freetier-agent-api__page_check",
"mcp__freetier-agent-api__link_check",
"mcp__freetier-agent-api__country",
"mcp__freetier-agent-api__holidays",
"mcp__freetier-agent-api__currency",
"mcp__freetier-agent-api__base_gas",
"mcp__freetier-agent-api__page_markdown",
"mcp__freetier-agent-api__email_verify",
"mcp__freetier-agent-api__extract_json",
"mcp__freetier-agent-api__gas",
"mcp__freetier-agent-api__token_info",
"mcp__freetier-agent-api__ens",
"mcp__freetier-agent-api__dns",
"mcp__freetier-agent-api__domain_whois",
"mcp__freetier-agent-api__ssl_cert",
"mcp__freetier-agent-api__geocode",
"mcp__freetier-agent-api__feed_json",
"mcp__freetier-agent-api__sitemap",
"mcp__freetier-agent-api__qr_code",
"mcp__freetier-agent-api__free_tiers",
"mcp__freetier-agent-api__llm_pricing",
"mcp__freetier-agent-api__mcp_servers",
"mcp__freetier-agent-api__x402_services",
"mcp__freetier-agent-api__agent_tools",
"mcp__freetier-agent-api__dataset_full",
"mcp__freetier-agent-api__dump_mcp_servers",
"mcp__freetier-agent-api__dump_llm_pricing",
"mcp__freetier-agent-api__dump_world_reference",
"mcp__freetier-agent-api__dump_x402_services",
"mcp__freetier-agent-api__dump_agent_tools",
"mcp__freetier-agent-api__token_score",
"mcp__freetier-agent-api__token_portfolio",
"mcp__freetier-agent-api__rug_check",
"mcp__freetier-agent-api__token_price",
"mcp__freetier-agent-api__token_prices",
"mcp__freetier-agent-api__token_price_history",
"mcp__freetier-agent-api__news_monitor",
"mcp__freetier-agent-api__news_entity",
"mcp__freetier-agent-api__news_sentiment",
"mcp__freetier-agent-api__wiki_fact",
"mcp__freetier-agent-api__company_profile",
"mcp__freetier-agent-api__company_techstack",
"mcp__freetier-agent-api__company_contacts",
"mcp__freetier-agent-api__company_batch",
"mcp__freetier-agent-api__classify",
"mcp__freetier-agent-api__entity_extract",
"mcp__freetier-agent-api__translate",
"mcp__freetier-agent-api__email_verify_quick",
"mcp__freetier-agent-api__email_verify_batch",
"mcp__freetier-agent-api__geocode_batch",
"mcp__freetier-agent-api__pack_wallet_safety",
"mcp__freetier-agent-api__pack_website_to_rag",
"mcp__freetier-agent-api__pack_b2b_lead_finder",
"mcp__freetier-agent-api__pack_payment_verification",
"mcp__freetier-agent-api__pack_domain_health",
"mcp__freetier-agent-api__pack_ai_tool_discovery"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as freetier-agent-api. Review it before you use it.
Capability tags behind 70 rules
- mcp__freetier-agent-api__invoice_json untrusted-input, outbound
- mcp__freetier-agent-api__token_risk untrusted-input
- mcp__freetier-agent-api__tx_explain untrusted-input
- mcp__freetier-agent-api__wallet_profile untrusted-input
- mcp__freetier-agent-api__contract_abi untrusted-input
- mcp__freetier-agent-api__site_contacts untrusted-input, outbound
- mcp__freetier-agent-api__page_rag untrusted-input, outbound
- mcp__freetier-agent-api__robots_check untrusted-input, outbound
- mcp__freetier-agent-api__page_meta untrusted-input, outbound
- mcp__freetier-agent-api__llm_cost untrusted-input
- mcp__freetier-agent-api__page_check untrusted-input, outbound
- mcp__freetier-agent-api__link_check untrusted-input, outbound
- mcp__freetier-agent-api__country untrusted-input
- mcp__freetier-agent-api__holidays untrusted-input
- mcp__freetier-agent-api__currency untrusted-input, outbound
- mcp__freetier-agent-api__base_gas untrusted-input
- mcp__freetier-agent-api__page_markdown untrusted-input, outbound
- mcp__freetier-agent-api__email_verify untrusted-input
- mcp__freetier-agent-api__extract_json untrusted-input
- mcp__freetier-agent-api__gas untrusted-input
- mcp__freetier-agent-api__token_info untrusted-input
- mcp__freetier-agent-api__ens untrusted-input
- mcp__freetier-agent-api__tx_status untrusted-input
- mcp__freetier-agent-api__dns untrusted-input
- mcp__freetier-agent-api__domain_whois untrusted-input
- mcp__freetier-agent-api__ssl_cert untrusted-input
- mcp__freetier-agent-api__geocode untrusted-input
- mcp__freetier-agent-api__feed_json untrusted-input, outbound
- mcp__freetier-agent-api__sitemap untrusted-input, outbound
- mcp__freetier-agent-api__qr_code untrusted-input
- mcp__freetier-agent-api__apis_search untrusted-input
- mcp__freetier-agent-api__free_tiers untrusted-input
- mcp__freetier-agent-api__llm_pricing untrusted-input
- mcp__freetier-agent-api__mcp_servers untrusted-input
- mcp__freetier-agent-api__x402_services untrusted-input
- mcp__freetier-agent-api__agent_tools untrusted-input
- mcp__freetier-agent-api__dataset_full untrusted-input
- mcp__freetier-agent-api__dump_mcp_servers untrusted-input
- mcp__freetier-agent-api__dump_llm_pricing untrusted-input
- mcp__freetier-agent-api__dump_world_reference untrusted-input
- mcp__freetier-agent-api__dump_x402_services untrusted-input
- mcp__freetier-agent-api__dump_agent_tools untrusted-input
- mcp__freetier-agent-api__token_score untrusted-input
- mcp__freetier-agent-api__token_portfolio untrusted-input
- mcp__freetier-agent-api__token_compare untrusted-input
- mcp__freetier-agent-api__rug_check untrusted-input
- mcp__freetier-agent-api__token_price untrusted-input
- mcp__freetier-agent-api__token_prices untrusted-input
- mcp__freetier-agent-api__token_price_history untrusted-input
- mcp__freetier-agent-api__news_monitor untrusted-input
- mcp__freetier-agent-api__news_entity untrusted-input
- mcp__freetier-agent-api__news_sentiment untrusted-input
- mcp__freetier-agent-api__wiki_fact untrusted-input
- mcp__freetier-agent-api__company_profile untrusted-input
- mcp__freetier-agent-api__company_techstack untrusted-input
- mcp__freetier-agent-api__company_contacts untrusted-input
- mcp__freetier-agent-api__company_batch untrusted-input
- mcp__freetier-agent-api__summarize untrusted-input
- mcp__freetier-agent-api__classify untrusted-input
- mcp__freetier-agent-api__entity_extract untrusted-input
- mcp__freetier-agent-api__translate untrusted-input, outbound
- mcp__freetier-agent-api__email_verify_quick untrusted-input
- mcp__freetier-agent-api__email_verify_batch untrusted-input
- mcp__freetier-agent-api__geocode_batch untrusted-input
- mcp__freetier-agent-api__pack_wallet_safety untrusted-input
- mcp__freetier-agent-api__pack_website_to_rag untrusted-input, outbound
- mcp__freetier-agent-api__pack_b2b_lead_finder untrusted-input, outbound
- mcp__freetier-agent-api__pack_payment_verification untrusted-input
- mcp__freetier-agent-api__pack_domain_health untrusted-input, outbound
- mcp__freetier-agent-api__pack_ai_tool_discovery untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.pages.freetier-agent-api/freetier-agent-api/verify?hash=3fe028965896add3858296a9b37f80e54387698da1f509ecca32668e790269b7" | jq -e '.changed == false'Pinned hash 3fe028965896, from Nov 9, 2026, 10:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.pages.freetier-agent-api/freetier-agent-api/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.pages.freetier-agent-api/freetier-agent-api)Source: MCP Registry. Synced Oct 26, 2026, 13:17 UTC.
FreeTier Agent API MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the FreeTier Agent API MCP server safe?
- No scan can promise that. What its definitions show: 74 tools, 68 of which can change, send or delete something, and 6 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the FreeTier Agent API MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the FreeTier Agent API MCP server do things that cannot be undone?
- Yes. 4 tools can send, pay, publish or merge: invoice_json, currency, translate and pack_payment_verification.
What tools does the FreeTier Agent API MCP server have?
- 74 tools: 4 irreversible, 64 write, 6 read. invoice_json, currency, translate, pack_payment_verification, mcp_servers_sample, llm_pricing_sample, api_directory_sample, token_risk and 66 more.
Does the FreeTier Agent API MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the FreeTier Agent API MCP server send data to outside services?
- 15 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): invoice_json, site_contacts, page_rag, robots_check, page_meta, page_check and 9 more.
Has the FreeTier Agent API MCP server changed its tools?
- Yes, 5 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.