MCP MeasureMCP Measure

索引已觀測

Context Atlas

Find llms.txt, docs, MCP servers, skills and CLIs for a tech stack, for coding agents.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
97%
命名品質
100%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~437Token（工具定義）
~881 B典型回應大小
極小的注意力影響（128k 上下文的 0.34%）

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案：

{
  "mcpServers": {
    "contextatlas": {
      "url": "https://contextatlas.dev/mcp"
    }
  }
}

遠端端點

https://contextatlas.dev/mcpstreamable-http

它能做什麼

工具清單

工具（3）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search(query, kind, limit)

Full-text search over tools (topics) and their sources. Matches names, roles, regions, detection signals (files, dependencies, env vars), source titles and URLs. Every word must match, as a prefix.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Words to search for, e.g. \"database\", \"vercel mcp\" or \"turbo.json\""
    },
    "kind": {
      "description": "Only return sources of this kind",
      "type": "string",
      "enum": [
        "llms",
        "full",
        "docs",
        "mcp",
        "skill",
        "rules",
        "guide"
      ]
    },
    "limit": {
      "description": "Maximum number of topics, default 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_topic(id)

All sources (llms.txt, docs, MCP servers, skills, rules), detection signals and the role of one tool, by id such as `vercel`, `nextjs` or `drizzle`.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "description": "Topic id, as returned by search or list_topics"
    }
  },
  "required": [
    "id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_topics(region)

Every tool in the catalog with its id, name, role and region, without sources. Use it to find candidates per role, then get_topic and their llms.txt sources to compare them.

輸入結構描述

{
  "type": "object",
  "properties": {
    "region": {
      "description": "Only this region id, e.g. cloud, frameworks, standards or clis",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本3 個工具