Skills Plugins MCP Prompt Model 导航 博客 资讯 我的中心
Knowledge & Memory (RAG) #Python#远端可用#MIT

graph-tool-call

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Knowledge & Memory (RAG) 0 platforms 0 features

Install

uvx graph-tool-call

Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.

{
  "mcpServers": {
    "graph-tool-call": {
      "command": "uvx",
      "args": [
        "graph-tool-call"
      ],
      "env": {
        "graph": "<graph>",
        "config": "<config>",
        "source": "<source>"
      }
    }
  }
}

Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.

Sources: public MCP Server directories. This is an independent third-party directory with no affiliation to or endorsement from the maintainers of the listed servers.

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。