MCP MeasureMCP Measure

索引已觀測

runx

The governed runtime for agent skills. Search the catalog and inspect a skill before running it.

我該用這個嗎

品質與安全性

A
說明品質
90%
結構描述完整度
100%
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

~344Token（工具定義）
~1.0 KB典型回應大小
極小的注意力影響（128k 上下文的 0.27%）

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": {
    "runx": {
      "url": "https://api.runx.ai/mcp"
    }
  }
}

遠端端點

https://api.runx.ai/mcpstreamable-http

它能做什麼

工具清單

工具（2）

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

Find runx skills by what they do. Returns each match with its skill id, owner, description, latest version, and trust tier, so a caller can pick one and then read it in full with get_skill.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "What the skill should do, in plain words. An empty string browses everything."
    },
    "limit": {
      "description": "Maximum matches to return.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_skill(skill_id, version)

Read one runx skill in full before running it: its manifest, the authority it asks for, its publisher and trust signals, and the exact command to install and run it through the runx CLI. Everything needed to decide whether to trust a skill arrives in this one call.

輸入結構描述

{
  "type": "object",
  "properties": {
    "skill_id": {
      "type": "string",
      "minLength": 1,
      "description": "Skill id in owner/name form, for example `ausca/browser-session`."
    },
    "version": {
      "description": "Exact version to read. Defaults to the latest published version.",
      "type": "string"
    }
  },
  "required": [
    "skill_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

建議的提示詞

search_research
Search for information about [topic] using runx
預期的工具： search_skills
find_specific
Find [specific item] using runx
預期的工具： search_skills
retrieve_data
Get details about [item] from runx
預期的工具： get_skill
fetch_info
Fetch [information type] using runx
預期的工具： get_skill
research_workflow
Search for [topic], then get detailed information about the top results using runx
預期的工具： search_skillsget_skill

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本2 個工具
已驗證未記錄版本2 個工具