Agent Data Co

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

我该使用它吗

质量与安全性

A
描述质量
93%
模式完整度
75%
命名质量
98%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(3)

  • LOWTool 'get_momentum_leaderboard' description lacks action verb在 get_momentum_leaderboard 中
  • LOWTool 'get_mcp_servers' description lacks action verb在 get_mcp_servers 中
  • LOWTool 'get_hf_trending' description lacks action verb在 get_hf_trending 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,802token 数(工具定义)
~855 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.41%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

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

远程端点

https://agentdataco.com/mcpstreamable-http

它能做什么

工具清单

工具(12)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_momentum_leaderboard(feed, limit)

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).

输入模式

{
  "type": "object",
  "properties": {
    "feed": {
      "type": "string",
      "enum": [
        "github-ai-repos",
        "mcp-servers",
        "llm-pricing",
        "hf-trending"
      ]
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 25
    }
  }
}
🟢list_feeds

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

输入模式

{
  "type": "object",
  "properties": {}
}
🟢get_sample(feed)

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

输入模式

{
  "type": "object",
  "properties": {
    "feed": {
      "type": "string",
      "enum": [
        "github-ai-repos",
        "show-hn-ai",
        "mcp-servers",
        "hf-trending",
        "llm-pricing",
        "ai-pricing"
      ]
    }
  }
}
🟢lookup_entity(feed, 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).

输入模式

{
  "type": "object",
  "properties": {
    "feed": {
      "type": "string",
      "enum": [
        "github-ai-repos",
        "mcp-servers",
        "llm-pricing",
        "ai-pricing",
        "hf-trending"
      ]
    },
    "entity": {
      "type": "string"
    }
  },
  "required": [
    "feed",
    "entity"
  ]
}
🟢get_github_ai_repos(q, since, limit, offset, repo)

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).

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Case-insensitive full-text filter"
    },
    "since": {
      "type": "string",
      "description": "ISO date; only rows created/updated on or after"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000,
      "default": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0
    },
    "repo": {
      "type": "string"
    }
  }
}
🟢get_show_hn_ai(q, since, limit, offset)

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

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Case-insensitive full-text filter"
    },
    "since": {
      "type": "string",
      "description": "ISO date; only rows created/updated on or after"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000,
      "default": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0
    }
  }
}
🟢get_mcp_servers(q, since, limit, offset)

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

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Case-insensitive full-text filter"
    },
    "since": {
      "type": "string",
      "description": "ISO date; only rows created/updated on or after"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000,
      "default": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0
    }
  }
}
🟢get_hf_trending(q, since, limit, offset)

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

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Case-insensitive full-text filter"
    },
    "since": {
      "type": "string",
      "description": "ISO date; only rows created/updated on or after"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000,
      "default": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0
    }
  }
}
🟢get_llm_pricing(q, since, limit, offset)

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

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Case-insensitive full-text filter"
    },
    "since": {
      "type": "string",
      "description": "ISO date; only rows created/updated on or after"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000,
      "default": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0
    }
  }
}
🟢get_ai_pricing(q, since, limit, offset, url)

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).

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Case-insensitive full-text filter"
    },
    "since": {
      "type": "string",
      "description": "ISO date; only rows created/updated on or after"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000,
      "default": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0
    },
    "url": {
      "type": "string"
    }
  }
}
🟢get_history(feed, entity, from, to, limit, ...)

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, [email protected]. Requires API key.

输入模式

{
  "type": "object",
  "properties": {
    "feed": {
      "type": "string",
      "enum": [
        "github-ai-repos",
        "show-hn-ai",
        "mcp-servers",
        "hf-trending",
        "llm-pricing",
        "ai-pricing"
      ]
    },
    "entity": {
      "type": "string",
      "description": "owner/repo, MCP server name, OpenRouter model id, pricing page URL, \"model:<hf id>\", HN item id"
    },
    "from": {
      "type": "string",
      "description": "YYYY-MM-DD (default: to minus 30 days)"
    },
    "to": {
      "type": "string",
      "description": "YYYY-MM-DD (default today); max 90 days after from"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 90,
      "default": 31
    },
    "cursor": {
      "type": "string",
      "description": "nextCursor from the previous page"
    }
  },
  "required": [
    "feed",
    "entity"
  ]
}
🟢get_trends(window, feed, date)

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 daily history/trends fair-use cap (200 Starter / 1,000 Pro). Requires API key.

输入模式

{
  "type": "object",
  "properties": {
    "window": {
      "type": "string",
      "enum": [
        "1d",
        "7d",
        "30d"
      ]
    },
    "feed": {
      "type": "string",
      "enum": [
        "github-ai-repos",
        "show-hn-ai",
        "mcp-servers",
        "hf-trending",
        "llm-pricing",
        "ai-pricing"
      ]
    },
    "date": {
      "type": "string",
      "description": "YYYY-MM-DD (default latest; requires feed)"
    }
  }
}

社区

评价此服务器

证据

最近观测

已验证未记录版本12 个工具