MCP.so
ログイン

llm-mcp

@genomoncology

リポジトリ

llm-mcp について

llm plugin of MCP for clients and servers.

#llm-mcp#plugin#mcp

基本情報

カテゴリ

AI とエージェント

ライセンス

MIT license

ランタイム

python

トランスポート

stdio

公開者

genomoncology

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "llm-mcp": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "llm"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is llm-mcp?

llm-mcp is an LLM plugin that adds Model Context Protocol (MCP) support, enabling LLMs to use tools from any MCP server. It integrates with the LLM command-line tool and is designed for users who want to extend their LLMs with external tools via MCP.

How to use llm-mcp?

Install LLM 0.26+ and the plugin with llm install llm-mcp. Then add MCP servers using llm mcp servers add <url> (remote) or llm mcp servers add "npx ..." (local). Added tools become available via the -T flag when running LLM models.

Key features of llm-mcp?

  • Add remote and local MCP servers.
  • List, view, and remove MCP servers.
  • Convert MCP tools to LLM tools.
  • Support for stdio and HTTP servers.
  • Debug mode with the --td flag.

Use cases of llm-mcp?

  • Use MCP tools to read files and answer questions.
  • Chain multiple tools to search documentation and fetch URLs.
  • Enable LLMs to interact with system tools like Desktop Commander.
  • Manage tool collections (roadmap includes toolboxes and proxy).

FAQ from llm-mcp

What are the requirements for llm-mcp?

Requires LLM version 0.26 or higher and Python 3.10+.

What transport protocols does llm-mcp support?

It supports stdio and HTTP servers for MCP connections.

Is llm-mcp safe to use?

The README warns that tools can be dangerous; care is needed when enabling tools with untrusted content.

How do I add an MCP server to llm-mcp?

Use llm mcp servers add <url> for remote servers or llm mcp servers add "npx ..." for local servers.

Can I see debug information about tool calls?

Yes, use the --td flag with your LLM command to see tool calls in debug mode.

コメント

「AI とエージェント」の他のコンテンツ

Gemini MCP Server

aliargun

MCP server implementation for Google's Gemini API

259

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

Hass-MCP

voska

Control and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.

307

🔎 GPT Researcher

assafelovic

An autonomous agent that conducts deep research on any data using any LLM providers

28.1K

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416