Agent Data API MCP server
io.github.Bustlll/agent-data-apiBustlllstreamable-httpv1.0.1Scanned
Memecoin screener, backtests, exit alerts, wallet traces + web search, enrichment, 50+ tools (x402)
10 tools: 5 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 10
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. 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 Agent Data API MCP server can do
The Agent Data API MCP server is published by the GitHub account Bustlll. It has 10 tools. It can create or change data (5 tools: company_enrich, email_verify, token_check, address_check and 1 more), but cannot delete data. 5 tools only read.
1 tool reads private data (shopify_lookup); 10 tools bring in text other people can write (catalog_read, web_search, web_read and 7 more); 2 tools can send data out of your system (web_read and x402_lookup). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 8, 2026, version 1.0.1.
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.
10 tools
Changes things 5Claude Code: ask
address_checkScreen a wallet address (BTC, ETH/EVM, Solana, Tron, XRP, LTC) against OFAC sanctions and scam lists with on-chain context.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 Screen a wallet address (BTC, ETH/EVM, Solana, Tron, XRP, LTC) against OFAC sanctions and scam lists with on-chain context. tier=max adds the chain's own trail: a 2-hop Bitcoin trace with exposure, a Solana wallet's age and trading record, or a Base wallet's USDC counterparties. For tokens use token_check. Price: standard $0.02, max $0.10. Live; 2-20 s. Risk signals, not a legal finding. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
company_enrichEverything public about a company from its domain: name, description, size hints, address, phones, emails, socials, website platform, email provider and security, SaaS stack.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 Everything public about a company from its domain: name, description, size hints, address, phones, emails, socials, website platform, email provider and security, SaaS stack. tier=max adds its LinkedIn company page (employees, followers, industry, open jobs) and verifies each email found. For only email checks use email_verify. Price: standard $0.03, max $0.12. Reads the site live; 5-25 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
data_tool_runRuns one data tool with its JSON input: Google Maps places with contacts, YouTube videos / transcripts / comments, Indeed, LinkedIn and 13 other job boards, LinkedIn companies, Goo…Reads text others write1 finding
Why it is in this group
- The name "data_tool_run" says "run": 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.
Findings
- Warn
The server marks "data_tool_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "data_tool_run" says "run": a word for a change.
Description, as the server wrote it Runs one data tool with its JSON input: Google Maps places with contacts, YouTube videos / transcripts / comments, Indeed, LinkedIn and 13 other job boards, LinkedIn companies, Google News and Trends, Google Ads library, TikTok comments, Pinterest, Airbnb, Redfin, AliExpress, app stores, website contacts and SEO checks, sanctions, clinical trials and more. catalog_read what=prices lists every tool with an input example. Each tool has its own price, $0.01-0.08 per capped run (catalog_read what=prices). tier=max runs a bigger job for: google-maps-scraper ($0.35), indeed-jobs-scraper ($0.15), linkedin-company-scraper ($0.15), linkedin-jobs-scraper ($0.12), youtube-comments-scraper ($0.15). Runs live on Apify; 10 s-4 min. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
email_verifyCheck email addresses without sending mail: syntax, domain and MX records, disposable domains, role accounts, catch-all hints, and a valid / risky / invalid verdict each, plus a su…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 Check email addresses without sending mail: syntax, domain and MX records, disposable domains, role accounts, catch-all hints, and a valid / risky / invalid verdict each, plus a summary. Up to 20 addresses cost $0.01 per call; 21-200 addresses are a bulk call at $0.10. For company data use company_enrich. DNS lookups live; under 1 s for 20. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
token_checkCheck a token before trading.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 Check a token before trading. level=quick: one-line pre-trade verdict for up to 10 tokens ($0.02). level=safety (default): contract / mint safety: honeypot simulation, buy/sell tax, mint and freeze authority, Token-2022 traps, holders, liquidity ($0.015). level=max: safety plus the pre-trade verdict, one verdict and every red flag ($0.10). For wallets use address_check. Live data (chain, RugCheck, DexScreener); 1-30 s. Signals, not advice. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
Only reads 5Show 5 read-only tools
catalog_readFREE, no payment.Reads text others writeNo findings
Why it is in this group
- The name "catalog_read" says "read": 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 FREE, no payment. what=prices: every tool with its price per tier and an input example, plus the plain-HTTP x402 endpoint for each.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
shopify_lookupaction=store: one Shopify store's apps by category (reviews, email, subscriptions, loyalty...), pixels, theme and catalog hints, gaps and sales pitch angles.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "shopify_lookup" says "lookup": a word for reading.
What it can reach
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it action=store: one Shopify store's apps by category (reviews, email, subscriptions, loyalty...), pixels, theme and catalog hints, gaps and sales pitch angles. action=search: stores from our index of ~19k Shopify stores by app used / not used, missing category, country and keyword (lead lists). Price: store $0.02, search $0.05. Store reads are live (3-15 s); the index is refreshed weekly. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
web_readFetch one public URL and return its main content as clean markdown (title, publish date, word count) plus a prompt-injection verdict; raw=true returns the raw body instead (text or…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "web_read" says "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web_read" says "read" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch one public URL and return its main content as clean markdown (title, publish date, word count) plus a prompt-injection verdict; raw=true returns the raw body instead (text or base64). Give `text` instead of `url` to only scan text you already have for prompt injection. To find pages first use web_search. Price: read $0.004, raw $0.003, text scan $0.002. Fetched live via Cloudflare's network; 1-10 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
web_searchSearch the web: Google-quality results re-ranked for authority, merged with papers (arXiv), GitHub and news when the query needs them; optional category.Reads text others writeNo findings
Why it is in this group
- The name "web_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.
- untrusted-inputThe name "web_search" says "search" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it Search the web: Google-quality results re-ranked for authority, merged with papers (arXiv), GitHub and news when the query needs them; optional category. Use it to find pages; with read=N it also returns the full clean text of the top N pages; with research=true it reads up to 8 pages and extracts the passages that answer the query, with sources. For one known URL use web_read instead. Price: results only $0.006, read 1-5 pages $0.015, research $0.05. Returns titles, URLs, snippets (and page markdown with a prompt-injection verdict per page). Live results; 1-15 s. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
x402_lookupAnswers about the x402 agent-payments market from the whole Bazaar index and Base chain history.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "x402_lookup" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Answers about the x402 agent-payments market from the whole Bazaar index and Base chain history. action=recommend: which x402 API to call for a need, ranked by fit, price and trust ($0.01). seller_check: is an x402 endpoint / seller trustworthy, its prices and payers ($0.01). payer_profile: a Base wallet's x402 payments, sellers and counterparties up to 3 hops ($0.03). seller_customers: who pays a seller and how much ($0.05). payments_feed: a wallet's payments in time order, with a cursor ($0.005). Bazaar index refreshed every 6 h; chain data real time. Paid with x402 (USDC on Base, Polygon or Solana) per call; failed or empty calls are never charged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: 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.
20 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__agent-data-api__shopify_lookup"
]
}
}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 15, 2026, 13:22 UTC, unchanged since Oct 31, 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
- 5
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-data.centorprat.workers.dev/mcp: tools/list returned 10 tools to an anonymous client, including company_enrich (write), email_verify (write), token_check (write), address_check (write), data_tool_run (write)
Posture changes
- Oct 31, 2026
- Tools that change things, listed without credentials: 10 to 5
Findings
Matches of fixed checks, with the text they matched.
- Warndata_tool_run
The server marks "data_tool_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "data_tool_run" says "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools6 added, 25 removed, 4 changed.+6 added−25 removed~4 changedView diff
- Added:address_checkChanges things
- Added:catalog_readOnly reads
- Added:data_tool_runChanges things
- Added:shopify_lookupOnly reads
- Added:token_checkChanges things
- Added:x402_lookupOnly reads
- Removed:check_x402_seller
- Removed:crypto_address_risk
- Removed:list_tools_and_prices
- Removed:memecoin_alerts
- Removed:memecoin_backtest
- Removed:memecoin_exit_check
- Removed:memecoin_holder_trace
- Removed:memecoin_screen
- Removed:memecoin_token_report
- Removed:memecoin_track_record
- Removed:memecoin_watch
- Removed:payments_feed
- Removed:prompt_injection_check
- Removed:recommend_x402_api
- Removed:run_data_tool
- Removed:shopify_store
- Removed:shopify_stores_search
- Removed:solana_wallet_profile
- Removed:token_launches
- Removed:token_pretrade_check
- Removed:token_safety
- Removed:web_fetch
- Removed:web_search_read
- Removed:x402_payer_profile
- Removed:x402_seller_customers
- Changed:company_enrichChanges thingstitledescriptioninputSchemaannotations
- Changed:email_verifyChanges thingstitledescriptioninputSchemaannotations
- Changed:web_readOnly readstitledescriptioninputSchemaannotations
- Changed:web_searchOnly readstitledescriptioninputSchemaannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 10 -> 5.View diff
- Tools that change things, listed without credentials: 10 to 5
Tools11 added.+11 addedView diff
- Added:memecoin_alertsChanges things
- Added:memecoin_backtestChanges things
- Added:memecoin_exit_checkChanges things
- Added:memecoin_holder_traceChanges things
- Added:memecoin_screenChanges things
- Added:memecoin_token_reportChanges things
- Added:memecoin_track_recordChanges things
- Added:memecoin_watchChanges things
- Added:payments_feedCan't be undone
- Added:x402_payer_profileChanges things
- Added:x402_seller_customersChanges things
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-data-api https://agent-data.centorprat.workers.dev/mcpclaude mcp add --transport http agent-data-api https://agent-data.centorprat.workers.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__agent-data-api__catalog_read",
"mcp__agent-data-api__web_search",
"mcp__agent-data-api__shopify_lookup"
],
"ask": [
"mcp__agent-data-api__web_read",
"mcp__agent-data-api__company_enrich",
"mcp__agent-data-api__email_verify",
"mcp__agent-data-api__token_check",
"mcp__agent-data-api__address_check",
"mcp__agent-data-api__x402_lookup",
"mcp__agent-data-api__data_tool_run"
],
"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 agent-data-api. Review it before you use it.
Capability tags behind 10 rules
- mcp__agent-data-api__catalog_read untrusted-input
- mcp__agent-data-api__web_search untrusted-input
- mcp__agent-data-api__web_read untrusted-input, outbound
- mcp__agent-data-api__company_enrich untrusted-input
- mcp__agent-data-api__email_verify untrusted-input
- mcp__agent-data-api__token_check untrusted-input
- mcp__agent-data-api__address_check untrusted-input
- mcp__agent-data-api__x402_lookup untrusted-input, outbound
- mcp__agent-data-api__shopify_lookup private-data, untrusted-input
- mcp__agent-data-api__data_tool_run 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/io.github.Bustlll/agent-data-api/verify?hash=5b9060f535644736e616b7b39cd3ab99ac03c72ff6f7fd4f8aa475fea5df9fef" | jq -e '.changed == false'Pinned hash 5b9060f53564, from Nov 8, 2026, 22:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Bustlll/agent-data-api/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Bustlll/agent-data-api)Source: MCP Registry. Synced Oct 23, 2026, 22:17 UTC.
Agent Data API MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Data API MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 5 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agent Data 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 Agent Data API MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agent Data API MCP server have?
- 10 tools: 5 write, 5 read. company_enrich, email_verify, token_check, address_check, data_tool_run, catalog_read, web_search, web_read and 2 more.
Does the Agent Data API MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Data API MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): web_read and x402_lookup.
Has the Agent Data API MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.