Skip to content

agentsvc.io MCP server

io.agentsvc/servicesagentsvc.iostreamable-httpv2.6.1Scanned

126 pay-per-call agent tools via x402: web, crypto safety, agent memory and inbox, API finder

12 tools: 9 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 9 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 11
  • Can send data out · 2
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

9 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.
Govern this server →

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 agentsvc.io MCP server can do

The agentsvc.io MCP server is published by agentsvc.io, a domain the MCP Registry verified. It has 12 tools. It can create or change data (9 tools: call_service, email_verify, web_scrape, audio_transcribe and 5 more), but cannot delete data. 3 tools only read.

1 tool reads private data (ip_lookup); 11 tools bring in text other people can write (call_service, email_verify, web_scrape and 8 more); 2 tools can send data out of your system (web_scrape and web_scrape_batch). 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 (base64-blob). 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 15, 2026, version 2.6.1.

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.

12 tools

Changes things 9Claude Code: ask
  • audio_transcribeAudio transcription and speech to text: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detect…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
    Audio transcription and speech to text: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per call. Returns text, detected language, duration and segments with start and end seconds. Also available OpenAI-compatible at POST /v1/audio/transcriptions (multipart file, model whisper-1). Price: $0.01 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"audio_url":"https://agentsvc.io/samples/speech-en.mp3"}.

    Annotations the server declares

    • title: Speech to Text (Whisper Transcription)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • call_serviceRun any agentsvc.io service by name with its input, e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "call_service" says "call": a word for a change.

    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
    Run any agentsvc.io service by name with its input, e.g. {"service": "pdf-extract", "input": {"url": "https://..."}}. Use find_service first to get the name and input schema. Costs $0.0015 to $0.6 USDC depending on the service (shown by find_service), paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum); x402 MCP clients such as @x402/mcp pay automatically. The example input of each service is a free sample.

    Annotations the server declares

    • title: Call any service
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
  • email_verifyEmail verification: checks whether an email address really exists by asking its mail server (SMTP RCPT TO probe; no email is sent), on top of syntax, MX, disposable and role checks…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
    Email verification: checks whether an email address really exists by asking its mail server (SMTP RCPT TO probe; no email is sent), on top of syntax, MX, disposable and role checks. Returns status deliverable, undeliverable (mailbox does not exist), catch_all (domain accepts any address), risky (disposable or mailbox full) or unknown (greylisting, server refused the check), plus the raw SMTP reply. Use it before sending outreach, to clean lead lists or to block fake sign-ups. Results are cached 6 hours. Params: email (required). Price: $0.002 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"email":"support@microsoft.com"}.

    Annotations the server declares

    • title: Email Deliverability Verification (SMTP)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • satellite_imageDaily true-color satellite image of any area from NASA GIBS (MODIS Terra/Aqua or VIIRS, about 250 m per pixel, coastlines overlaid) as base64 JPEG.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
    Daily true-color satellite image of any area from NASA GIBS (MODIS Terra/Aqua or VIIRS, about 250 m per pixel, coastlines overlaid) as base64 JPEG. Useful to see clouds, smoke, snow, floods or fires on a given day. Params: place ("Zurich, Switzerland") or bbox [min_lat, min_lon, max_lat, max_lon] or lat + lon + radius_km (5 to 500, default 50), date (YYYY-MM-DD, default yesterday), layer (modis_terra default, modis_aqua, viirs_snpp, viirs_noaa20), width (64 to 1024, default 512), height (default from aspect). Price: $0.013 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"lat":47.37,"lon":8.54,"radius_km":60,"width":512}.

    Annotations the server declares

    • title: Satellite Image (NASA)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • sec_filingsUS public company data from SEC EDGAR: company profile, recent filings (10-K, 10-Q, 8-K, Form 4 insider trades, S-1 ...) with direct document links, and optionally the latest annua…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
    US public company data from SEC EDGAR: company profile, recent filings (10-K, 10-Q, 8-K, Form 4 insider trades, S-1 ...) with direct document links, and optionally the latest annual financials (revenue, net income, assets, liabilities, equity, operating cash flow, diluted EPS). Params: ticker or cik (one required), forms (filter, e.g. ['10-K','8-K']), limit (1 to 50, default 10), include_financials (default false). Price: $0.0025 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"ticker":"AAPL","forms":["10-K","10-Q"],"limit":5,"include_financials":true}.

    Annotations the server declares

    • title: SEC Filings (EDGAR)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • token_verdictInstant buy-or-avoid verdict for a token, with a shareable result page and preview card (share_url): send a contract address (Base, Ethereum, BSC, Arbitrum, Polygon, Avalanche, Opt…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

    • Warn

      The description contains a 42-character base64 string.

      Matched text

      description: "...ple input {"token":"0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed","chain":"base"}."

      What this check looks for
    Description, as the server wrote it
    Instant buy-or-avoid verdict for a token, with a shareable result page and preview card (share_url): send a contract address (Base, Ethereum, BSC, Arbitrum, Polygon, Avalanche, Optimism) or a Solana mint, get a grade A to F, a label (SAFE, CAUTION, RISKY, DANGER), a 0 to 100 score and a one-line reason, built from real checks: honeypot sell simulation, buy and sell tax, mint, freeze and owner powers, owner powers in the contract code, DEX liquidity and token age, all computed by us on the blockchain. Young or illiquid tokens can never grade above C. Also returns key facts and a share_text. Params: token (address; tokenAddress also accepted), chain (default base; solana auto-detected). Price: $0.009 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"token":"0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed","chain":"base"}.

    Annotations the server declares

    • title: Token Verdict (grade A to F)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • translateTranslate text between 21 languages: en, de, fr, es, it, pt, nl, pl, sv, cs, el, ru, uk, tr, ar, hi, id, vi, zh, ja, ko.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
    Translate text between 21 languages: en, de, fr, es, it, pt, nl, pl, sv, cs, el, ru, uk, tr, ar, hi, id, vi, zh, ja, ko. Runs on our own server (Argos Translate), so the text is not sent to a third party. Max 1000 characters per call. source_lang defaults to auto-detect; confidence is the detection confidence. Pairs without a direct model are translated via English. Price: $0.009 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"text":"Hello, how are you?","target_lang":"de"}.

    Annotations the server declares

    • title: Text Translation
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • web_scrapeWeb page to markdown: read any web page (URL) as clean, LLM-ready Markdown, the web scraper for agents.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.
    • untrusted-inputThe name "web_scrape" says "scrape": 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.
    Description, as the server wrote it
    Web page to markdown: read any web page (URL) as clean, LLM-ready Markdown, the web scraper for agents. Default tool for reading ONE web page whose URL you have: returns clean Markdown (title, meta description, main content with headings, lists and links); Markdown and plain-text files such as llms.txt or README.md come back unchanged, PDFs as extracted text, JSON APIs pretty-printed. The fastest and cheapest way to give an LLM the content of a page. If a JavaScript app comes back nearly empty, set render:true (real browser, slower, plain text) or use webpage-reader. For 2 to 5 URLs use web-read-batch, for 6 to 20 web-scrape-batch (one payment), for a whole site site-crawl, and if you have a question but no URL search-read. Params: url (required), max_chars (default 8000, max 60000), include_links, render. Price: $0.0015 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"url":"https://example.com","max_chars":8000}.

    Annotations the server declares

    • title: Web Scrape (URL to Markdown)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • web_scrape_batchBulk web scraper: read up to 20 web pages in ONE paid call, each as clean, LLM-ready Markdown with title and meta description.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.
    • untrusted-inputThe name "web_scrape_batch" says "scrape": it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Bulk web scraper: read up to 20 web pages in ONE paid call, each as clean, LLM-ready Markdown with title and meta description. One payment instead of 20, pages fetched in parallel, duplicate URLs read once. Use when your agent works through a list of URLs (search results, product pages, a sitemap, a link list). A failed page is reported with its error while the others still return; charged only if at least one page was read. For a single URL use web-scrape, to find the URLs of one site first use site-map. Params: urls (1 to 20, required), max_chars per page (500 to 30000, default 8000), include_links. Price: $0.03 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"urls":["https://example.com/","https://agentsvc.io/","https://agentsvc.io/docs"],"max_chars":3000}.

    Annotations the server declares

    • title: Web Scrape Batch (up to 20 URLs to Markdown)
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • find_serviceFree.No findings

    Why it is in this group

    • The name "find_service" says "find": a word for reading.
    Description, as the server wrote it
    Free. Search all 127 agentsvc.io services by task (e.g. "transcribe audio", "company register", "token rug pull", "pdf to text"). Returns the best matches with price, input schema and a free example input. Then run one with call_service.

    Annotations the server declares

    • title: Find a service
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • ip_lookupIP lookup and geolocation: resolve any public IPv4 or IPv6 address to location and network data from a local database (no third-party call, answers in milliseconds): country, count…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "ip_lookup" says "lookup": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "database": it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    IP lookup and geolocation: resolve any public IPv4 or IPv6 address to location and network data from a local database (no third-party call, answers in milliseconds): country, country_code, region, city, lat/lon, IANA timezone, continent, is_eu, ASN with organization (isp, org, asn). Use for fraud and bot checks, geo-routing, analytics, or tagging traffic. Invalid, private and reserved addresses are rejected for free. Params: ip (defaults to the caller's IP). IP Geolocation by DB-IP (https://db-ip.com), CC BY 4.0. Price: $0.0055 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"ip":"8.8.8.8"}.

    Annotations the server declares

    • title: IP Geolocation
    • readOnlyHint: true
    • destructiveHint: false
    • 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.

22 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 write11
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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__services__ip_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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:55 UTC, unchanged since Oct 29, 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
9
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 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agentsvc.io/mcp: tools/list returned 12 tools to an anonymous client, including call_service (write), email_verify (write), web_scrape (write), audio_transcribe (write), satellite_image (write) and 4 more

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 100 to 9

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The description contains a 42-character base64 string.

    Matched text

    description: "...ple input {"token":"0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed","chain":"base"}."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 changed.~3 changedView diff
  2. Tools2 added, 120 removed, 4 changed.+2 added−120 removed~4 changedView diff
    • Added:call_serviceChanges things
    • Added:find_serviceOnly reads
    • Removed:accessibility_check
    • Removed:agent_inbox
    • Removed:agent_memory
    • Removed:agent_run
    • Removed:airport_status
    • Removed:answer_with_sources
    • Removed:barcode
    • Removed:btc_address
    • Removed:btc_fees
    • Removed:btc_timestamp
    • Removed:btc_timestamp_verify
    • Removed:btc_tx
    • Removed:btc_watch
    • Removed:chart_render
    • Removed:citation_check
    • Removed:company_brief
    • Removed:company_enrich
    • Removed:company_lookup
    • Removed:crypto_news
    • Removed:crypto_prices
    • Removed:cve_lookup
    • Removed:defi_tvl
    • Removed:defi_yields
    • Removed:dev_search
    • Removed:diagram_render
    • Removed:discussion_search
    • Removed:dns_lookup
    • Removed:doc_convert
    • Removed:doc_parse
    • Removed:domain_check
    • Removed:domain_compliance
    • Removed:email_validate
    • Removed:erc20_info
    • Removed:erc20_transfers
    • Removed:evm_balance
    • Removed:evm_tx
    • Removed:exchange_rates
    • Removed:feed_watch
    • Removed:gas_price
    • Removed:geocode
    • Removed:holidays
    • Removed:html_to_pdf
    • Removed:hyperliquid
    • Removed:iban_validate
    • Removed:image_alt_text
    • Removed:image_resize
    • Removed:invoice_extract
    • Removed:iota_address
    • Removed:iota_network
    • Removed:iota_notarize
    • Removed:iota_tx
    • Removed:iota_verify
    • Removed:iota_watch
    • Removed:kyb_check
    • Removed:language_detect
    • Removed:macro_data
    • Removed:news_sentiment
    • Removed:ocr
    • Removed:package_check
    • Removed:page_extract
    • Removed:page_summarize
    • Removed:page_watch
    • Removed:paper_search
    • Removed:pdf_extract
    • Removed:perp_funding
    • Removed:phone_validate
    • Removed:pii_redact
    • Removed:postal_code
    • Removed:prediction_markets
    • Removed:privacy_check
    • Removed:product_lookup
    • Removed:prompt_injection_check
    • Removed:qr_code
    • Removed:research_report
    • Removed:rss_fetch
    • Removed:sanctions_screen
    • Removed:satellite_compare
    • Removed:scam_message_check
    • Removed:screenshot
    • Removed:search_read
    • Removed:seo_meta
    • Removed:service_finder
    • Removed:site_audit
    • Removed:site_crawl
    • Removed:site_map
    • Removed:ssl_check
    • Removed:sui_address
    • Removed:sui_network
    • Removed:sui_tx
    • Removed:sui_watch
    • Removed:tech_stack
    • Removed:text_classify
    • Removed:text_embed
    • Removed:timezone
    • Removed:token_ai_verdict
    • Removed:token_flows
    • Removed:token_liquidity
    • Removed:token_precheck
    • Removed:token_security
    • Removed:token_simulate
    • Removed:token_smart_money
    • Removed:token_watch
    • Removed:trends_hot
    • Removed:tron_address
    • Removed:tron_watch
    • Removed:tts
    • Removed:url_status
    • Removed:useragent_parse
    • Removed:vat_validate
    • Removed:vin_decode
    • Removed:wallet_portfolio
    • Removed:wallet_watch
    • Removed:watch_create
    • Removed:watch_delete
    • Removed:watch_list
    • Removed:weather
    • Removed:web_read_batch
    • Removed:web_search
    • Removed:webpage_reader
    • Removed:whois
    • Changed:audio_transcribeChanges thingsdescription
    • Changed:email_verifyChanges thingsdescription
    • Changed:news_searchOnly readsdescription
    • Changed:web_scrapeChanges thingsdescription
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 100 -> 9.View diff
    • Tools that change things, listed without credentials: 100 to 9

Install

Pinned to version 2.6.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http services https://agentsvc.io/mcp
claude mcp add --transport http services https://agentsvc.io/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__services__find_service",
      "mcp__services__news_search",
      "mcp__services__ip_lookup"
    ],
    "ask": [
      "mcp__services__call_service",
      "mcp__services__email_verify",
      "mcp__services__web_scrape",
      "mcp__services__audio_transcribe",
      "mcp__services__satellite_image",
      "mcp__services__token_verdict",
      "mcp__services__translate",
      "mcp__services__web_scrape_batch",
      "mcp__services__sec_filings"
    ],
    "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 services. Review it before you use it.

Capability tags behind 11 rules
  • mcp__services__call_service untrusted-input
  • mcp__services__email_verify untrusted-input
  • mcp__services__web_scrape untrusted-input, outbound
  • mcp__services__audio_transcribe untrusted-input
  • mcp__services__satellite_image untrusted-input
  • mcp__services__news_search untrusted-input
  • mcp__services__token_verdict untrusted-input
  • mcp__services__translate untrusted-input
  • mcp__services__ip_lookup private-data, untrusted-input
  • mcp__services__web_scrape_batch untrusted-input, outbound
  • mcp__services__sec_filings 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.agentsvc/services/verify?hash=43d8d97af2b29e477537b8fd5f6342793a3a6b6f8220821ea6aa96cb223ff9f7" | jq -e '.changed == false'

Pinned hash 43d8d97af2b2, from Nov 15, 2026, 13:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.agentsvc/services/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.agentsvc/services
[![Anlyon Radar](https://radar.anlyon.com/badge/io.agentsvc/services.svg)](https://radar.anlyon.com/servers/io.agentsvc/services)

Source: MCP Registry. Synced Oct 21, 2026, 18:13 UTC.

agentsvc.io MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the agentsvc.io MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 9 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 agentsvc.io MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the agentsvc.io 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 agentsvc.io MCP server have?

12 tools: 9 write, 3 read. call_service, email_verify, web_scrape, audio_transcribe, satellite_image, token_verdict, translate, web_scrape_batch and 4 more.

Does the agentsvc.io MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the agentsvc.io 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_scrape and web_scrape_batch.

Has the agentsvc.io MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.