经 AI Skill Hub 精选评估,Metatron 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Metatron 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Metatron 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/kerbelp/metatron
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"metatron": {
"command": "npx",
"args": ["-y", "metatron"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Metatron 执行以下任务... Claude: [自动调用 Metatron MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"metatron": {
"command": "npx",
"args": ["-y", "metatron"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="assets/metatron-logo.png" alt="Metatron" width="180" height="180" /> </p>
ingest, triage, refine-feedback). serve, ui, and candidates are fully local and need no key.Note: The installer automatically downloads and manages uv and Python 3.12+ in an isolated user directory, so you do not need to pre-install them.
To install metatron as a global tool on your PATH:
curl -sSf https://getmetatron.com/install.sh | sh
To run it locally from source or contribute to the project:
git clone https://github.com/kerbelp/metatron.git
cd metatron
uv sync # create the venv and install dependencies
uv run metatron --help
To install from your local clone as a global tool:
uv tool install .
metatron ingest /path/to/your/repo # 1. bootstrap candidates (needs API key)
metatron candidates list # 2. review …
metatron candidates approve <id> # … and curate
metatron serve --repo <id> # 3. serve canonical priors over MCP
ingest prints the <id> to use for serve. To wire it into a coding agent automatically, see Connecting a coding agent.
Secrets come from the environment only. The CLI auto-loads a .env from the working directory (it never overrides an already-exported variable, and .env is gitignored):
```bash
ANTHROPIC_API_KEY=sk-ant-...
…or `export ANTHROPIC_API_KEY=sk-ant-...` directly.
**Non-secret settings** live in an optional `metatron.toml` (environment variables
`METATRON_DB` / `METATRON_MODEL` override it):
toml [metatron] db_path = "metatron.db" # one SQLite file holds many repos model = "claude-sonnet-4-6" # default extraction model ```
If you wire the server up yourself instead of using the script:
{
"mcpServers": {
"metatron": {
"command": "uv",
"args": ["run", "--project", "/abs/path/to/metatron", "metatron", "serve", "--repo", "github.com/acme/app"],
"env": { "METATRON_DB": "/abs/path/to/metatron.db" }
}
}
}
$ metatron --help
usage: metatron [-h] {ingest,serve,repo,ui,triage,refine-feedback,candidates} ...
positional arguments:
{ingest,serve,repo,ui,triage,refine-feedback,candidates}
ingest bootstrap candidate priors from a repo
serve serve one repo's priors to agents over MCP
repo inspect the repos in the store
ui launch the local curation web UI
triage run the advisory judge over candidate priors (does not auto-curate)
refine-feedback reshape captured agent feedback into structured candidate priors (Opus)
candidates review and curate candidate priors
| Dimension | Code RAG (e.g., Cursor, Copilot) | Code Graphs (e.g., Graphify) | Metatron (Priors) |
|---|---|---|---|
| **Primary Focus** | Text similarity search | Code architecture & call chains | Intent, gotchas & conventions |
| **Primary Data Source** | Raw source files | Abstract Syntax Trees (AST) | Git logs + Developer feedback |
| **What it Captures** | What code is written *where* | How files/functions are connected | *Why* decisions were made |
| **Curation Gate** | None (fully automated) | None (fully automated) | **Curated (Human-in-the-loop)** |
| **Best For** | Finding code examples & functions | System navigation & exploration | Writing code like a team senior |
Metatron是一个有潜力的开源MCP工具
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:Metatron 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | metatron |
| 原始描述 | 开源MCP工具:Metatron is a self-hosted system that captures a codebase's real implementation 。⭐7 · Python |
| Topics | mcpai-toolspython |
| GitHub | https://github.com/kerbelp/metatron |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-06-03 · 更新时间:2026-06-06 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端