MCP.so
登录

llm-mcp

@genomoncology

关于 llm-mcp

llm plugin of MCP for clients and servers.

基本信息

分类

AI 与智能体

许可证

MIT license

运行时

python

传输方式

stdio

发布者

genomoncology

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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.

评论

AI 与智能体 分类下的更多 MCP 服务器