Skip to content
Agent Data Co logo

Agent Data Co MCP server

Which MCP servers are Agent Data Co's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-27

← Back to Agent Data Co

Whose server it is
  • Registry namecom.agentdataco/apiverified in the MCP registry

The registry name sits under agentdataco.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools12
  • Server calls itselfagentdataco
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 98 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: compare LLM API prices per million tokens across providers; monitor SaaS pricing pages for plan changes.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "compare LLM API prices per million tokens across providers", the likely first call is get_llm_pricing.
  • For "monitor SaaS pricing pages for plan changes", the likely first call is get_ai_pricing.
  • Parameters are untyped or undescribed in 11 of 12 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer146 ms
  • Space in an agent's context≈ 1,608 tokensthe definitions of all its tools (12), which an agent carries on every turn
  • Tool definitionsB · 85 of 100
  • Typed results0 of 12 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 11 of 12

What an agent can do with it

  • can do · compare LLM API prices per million tokens across providers
  • not sure · track new MCP servers and AI agent repos on GitHub
  • can do · monitor SaaS pricing pages for plan changes

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers12 tools · read 2026-10-27
  • get_momentum_leaderboard

    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…

  • list_feeds

    List the Agent Data Co feeds (AI-ecosystem datasets), their sources and update times. Free, no API key.

  • get_sample

    Free sample: 5 latest rows from one or all feeds. No API key needed.

  • lookup_entity

    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).

  • get_github_ai_repos

    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).

  • get_show_hn_ai

    Show HN AI launches (source: Algolia HN Search API). Full current feed, refreshed daily. Requires API key.

  • get_mcp_servers

    Official MCP registry servers (source: registry.modelcontextprotocol.io). Full current feed, refreshed daily. Requires API key.

  • get_hf_trending

    Hugging Face trending models & Spaces (source: Hugging Face Hub API). Full current feed, refreshed daily. Requires API key.

  • get_llm_pricing

    LLM model pricing (OpenRouter) (source: OpenRouter models API). Full current feed, refreshed daily. Requires API key.

  • get_ai_pricing

    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).

  • get_history

    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…

  • get_trends

    Top movers (1d/7d/30d) by stars/likes/points plus change events: new entities, LLM price changes, MCP version bumps, pricing-page changes. Latest by default; past dates need `feed` and must be within your plan history. Counts toward the…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "api": {
      "type": "http",
      "url": "https://agentdataco.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http agentdataco https://agentdataco.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://agentdataco.com/mcp as a custom connector in the settings.

OpenAPI spec

12 paths, read 2026-10-27. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.