Skip to content

Agent Data Co MCP server

com.agentdataco/apiagentdataco.comstreamable-httpv1.0.0Scanned

Daily AI-ecosystem data: GitHub AI/MCP repos, MCP registry, HF trending, LLM pricing, with history.

12 tools: 12 only read.

Tools: 0 delete, 0 irreversible, 0 write, 12 read.
  • Reads private data · 3
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • 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 Agent Data Co MCP server can do

The Agent Data Co MCP server is published by agentdataco.com, a domain the MCP Registry verified. It has 12 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

3 tools read private data (get_momentum_leaderboard, lookup_entity and get_github_ai_repos); 2 tools bring in text other people can write (lookup_entity and get_ai_pricing); 1 tool can send data out of your system (get_ai_pricing). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 10, 2026, version 1.0.0.

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.

12 tools

Only reads 12Show 12 read-only tools
  • get_ai_pricingAI & SaaS pricing page snapshots (source: Public pricing pages).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_ai_pricing" says "get": a word for reading.

    What it can reach

    • 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
    AI & SaaS pricing page snapshots (source: Public pricing pages). Full current feed, refreshed daily. Requires API key. Pass url= for one pricing page (untracked pages are queued).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_github_ai_reposGitHub AI agent & MCP repos (source: GitHub Search API).Reads private dataNo findings

    Why it is in this group

    • The name "get_github_ai_repos" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_github_ai_repos" says "get" and "repo": it reads repositories.
    • private-dataThe description's first sentence says "repo": it reads repositories.
    • private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
    Description, as the server wrote it
    GitHub AI agent & MCP repos (source: GitHub Search API). Full current feed, refreshed daily. Requires API key. Pass repo=owner/name for one repo (untracked repos are queued).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_historyDaily time series for ONE entity from the append-only archive (Starter: last 30 days, Pro: full archive).No findings

    Why it is in this group

    • The name "get_history" says "get": a word for reading.
    Description, as the server wrote it
    Daily time series for ONE entity from the append-only archive (Starter: last 30 days, Pro: full archive). Max 90-day window per call (from..to); up to 90 rows per page, use nextCursor as `cursor` for the next page. No whole-feed dumps. Fair use: 200 (Starter) / 1,000 (Pro) history+trends calls per day per key; keys scanning many distinct entities/dates very fast are throttled for 1 hour (429). Bulk/full-archive access: data licence from $499/mo, hello@agentdataco.com. Requires API key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_llm_pricingLLM model pricing (OpenRouter) (source: OpenRouter models API).No findings

    Why it is in this group

    • The name "get_llm_pricing" says "get": a word for reading.
    Description, as the server wrote it
    LLM model pricing (OpenRouter) (source: OpenRouter models API). Full current feed, refreshed daily. Requires API key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_mcp_serversOfficial MCP registry servers (source: registry.modelcontextprotocol.io).No findings

    Why it is in this group

    • The name "get_mcp_servers" says "get": a word for reading.
    Description, as the server wrote it
    Official MCP registry servers (source: registry.modelcontextprotocol.io). Full current feed, refreshed daily. Requires API key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_momentum_leaderboardFree: ADC Momentum leaderboard (0-100 score from growth velocity, consistency, recency and agent demand in our daily archive) for GitHub AI repos, MCP servers, LLMs and Hugging Fac…Reads private dataNo findings

    Why it is in this group

    • The name "get_momentum_leaderboard" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "repo": it reads repositories.
    Description, as the server wrote it
    Free: ADC Momentum leaderboard (0-100 score from growth velocity, consistency, recency and agent demand in our daily archive) for GitHub AI repos, MCP servers, LLMs and Hugging Face items, plus what AI agents looked up most this week (Agent Demand Index).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_sampleFree sample: 5 latest rows from one or all feeds.No findings

    Why it is in this group

    • The name "get_sample" says "get": a word for reading.
    Description, as the server wrote it
    Free sample: 5 latest rows from one or all feeds. No API key needed.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_show_hn_aiShow HN AI launches (source: Algolia HN Search API).No findings

    Why it is in this group

    • The name "get_show_hn_ai" says "get": a word for reading.
    Description, as the server wrote it
    Show HN AI launches (source: Algolia HN Search API). Full current feed, refreshed daily. Requires API key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_feedsList the Agent Data Co feeds (AI-ecosystem datasets), their sources and update times.No findings

    Why it is in this group

    • The name "list_feeds" says "list": a word for reading.
    Description, as the server wrote it
    List the Agent Data Co feeds (AI-ecosystem datasets), their sources and update times. Free, no API key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • lookup_entityFree: latest public metrics and recent daily values for one tracked entity (top ~2,000 entities: GitHub repo owner/name, MCP server name, OpenRouter model id, pricing page URL, or …Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "repo": it reads repositories.
    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Free: latest public metrics and recent daily values for one tracked entity (top ~2,000 entities: GitHub repo owner/name, MCP server name, OpenRouter model id, pricing page URL, or hf "<type>:<id>"). Full history needs a key (get_history).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

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.

6 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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__api__get_ai_pricing"
    ]
  }
}

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, 18:33 UTC, unchanged since Oct 22, 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
0
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

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http api https://agentdataco.com/mcp
claude mcp add --transport http api https://agentdataco.com/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__api__get_momentum_leaderboard",
      "mcp__api__list_feeds",
      "mcp__api__get_sample",
      "mcp__api__lookup_entity",
      "mcp__api__get_github_ai_repos",
      "mcp__api__get_show_hn_ai",
      "mcp__api__get_mcp_servers",
      "mcp__api__get_hf_trending",
      "mcp__api__get_llm_pricing",
      "mcp__api__get_history",
      "mcp__api__get_trends"
    ],
    "ask": [
      "mcp__api__get_ai_pricing"
    ],
    "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 api. Review it before you use it.

Capability tags behind 4 rules
  • mcp__api__get_momentum_leaderboard private-data
  • mcp__api__lookup_entity private-data, untrusted-input
  • mcp__api__get_github_ai_repos private-data
  • mcp__api__get_ai_pricing untrusted-input, outbound

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/com.agentdataco/api/verify?hash=422404af7e84b6b3525631a3190e5a3ab7bef2ca36912cd2fa7019335d10aa02" | jq -e '.changed == false'

Pinned hash 422404af7e84, from Nov 10, 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/com.agentdataco/api/changes.xml

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

Badge

Anlyon Radar badge for com.agentdataco/api
[![Anlyon Radar](https://radar.anlyon.com/badge/com.agentdataco/api.svg)](https://radar.anlyon.com/servers/com.agentdataco/api)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:48 UTC.

Agent Data Co MCP server: questions and answers

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

Is the Agent Data Co MCP server safe?

No scan can promise that. What its definitions show: 12 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the Agent Data Co 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 Co 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 Co MCP server have?

12 tools: 12 read. get_momentum_leaderboard, list_feeds, get_sample, lookup_entity, get_github_ai_repos, get_show_hn_ai, get_mcp_servers, get_hf_trending and 4 more.

Does the Agent Data Co MCP server need sign-in or OAuth?

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

Does the Agent Data Co MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_ai_pricing.

Has the Agent Data Co MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.