warden 是一个 MCP 服务器,把多个 MCP 服务器和 Skills 隐藏在五个工具之后,按需提供搜索、调用、技能获取、管理和路由能力。

Stars

8

7 天增长

暂无数据

Fork 数

2

开放 Issue

8

开源协议

MIT

最近更新

2026-07-31

AI 仓库情报摘要
FR-AI / ANALYSIS

为什么值得关注

它通过只向智能体暴露五个工具、仅经显式搜索暴露工具或技能元数据,显著减少上下文占用,并可将 Claude Code 中的 MCP 服务器、插件和技能迁移到自己的注册表中,且支持备份和恢复。

适合谁使用

  • 希望减少上下文开销的 Claude Code 用户
  • 管理大量 MCP 服务器或工具的开发者
  • 希望统一智能体工具访问方式的团队
  • 使用 Claude Desktop、Cursor 等 MCP 兼容客户端的用户

典型使用场景

  • 将众多 MCP 工具统一收敛到 warden 这个 MCP 服务器之后
  • 把现有 Claude Code 中的 MCP 服务器、插件和技能迁移到 warden
  • 让智能体通过 admin 工具在运行时注册或移除工具
  • 根据规则和排序将任务路由到最合适的工具或技能

项目优势

  • 智能体上下文只包含 5 个工具定义,而不是所有下游工具
  • 搜索可基于正则和关键词对工具或技能的名称、描述和参数进行匹配
  • 迁移安全:默认先试运行、写入备份并支持 restore 恢复
  • 路由配置可通过 CLI 或 admin 工具即时生效

使用前须知

  • 被 warden 隐藏的 Skills 不会被 Claude Code 自动启动,需要用户指导模型先调用 search
  • call_tool 每次调用都会新建一个下游 MCP 连接,可能带来额外开销
  • 对 Claude Code 的迁移变更需要重启 Claude Code 才能生效

README 快速开始

warden

warden is one MCP server. It gives an agent access to many other MCP servers and Skills. The agent sees only 5 tools:

  • search(query, limit=5) — This tool does a regex or keyword search. It looks in the name, the description, and the arguments of each tool. It also looks in the name and the description of each Skill. No other data goes to the agent.
  • call_tool(server, name, arguments) — This tool sends a call to the MCP server that has the tool. Use a search result to find the server and the tool.
  • use_skill(name) — This tool returns the full instructions for a Skill. Use a search result to find the Skill.
  • admin(action, params) — This tool controls the registry. It can also move MCP servers and Skills out of Claude Code. The changes are immediate, and you do not restart the server. Refer to The admin tool.
  • route(task, context=None, mode=None) — This tool selects the best tool or Skill for a task. It ranks the candidates and returns the best one. It does not run the tool. Refer to Routing.

At start, warden connects one time to each MCP server in the configuration and gets its tools with list_tools. It also reads each Skill directory and finds the SKILL.md files. warden keeps this catalog on the server. The model does not get these definitions. The model gets only search results, and only when it asks.

How to use

The goal is to move your MCP servers and Skills behind warden. Then the Claude context has only the 5 tools. warden supplies the other data only when the agent asks for it.

  1. Install.

    pip install -r requirements.txt        # or: pip install .  (for the warden command)
    
  2. Test first (the safe method). The dry run shows each change. Then apply the migration to a temporary Claude home. warden does not change your real ~/.claude.

    warden migrate --all                                   # dry run: shows each change
    warden migrate --all --apply --home /tmp/fake-claude   # apply to a temporary home
    warden restore --id  --home /tmp/fake-claude
    
  3. Do the real migration. Remove --home to change your real Claude configuration. warden adds the items to the registry. warden also disables the ite

项目描述

One MCP server that fronts many MCP servers + Skills behind a small tool set and routes to the best one, keeping an agent's context tiny. Migrate your Claude Code MCPs/skills behind it.

相关仓库与替代方案

根据分类、Topic 和编程语言匹配的相似项目。

0xwilliamortiz
精选
0xwilliamortiz GitHub avatar

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI 与机器学习大语言模型
577
mereyabdenbekuly-ctrl
精选
mereyabdenbekuly-ctrl GitHub avatar

clodex-ide

Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.

AI 与机器学习AI 智能体
859
makecindy
精选
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI 与机器学习大语言模型
958