Skip to main content
Glama
deenesjakoruzh
Ritesh-977

codegraph-mcp

by Ritesh-977
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

codegraph-mcp

用于 GitHub 仓库的知识图谱 MCP 服务器。将任意 GitHub 仓库的代码导入 Neo4j 图（Repository / File / Function 节点；CONTAINS / DEFINES / IMPORTS / CALLS 边），并将该图作为只读 MCP 工具暴露给任何 MCP 主机——Claude Desktop、opencode、Cursor 或任何支持模型上下文协议的客户端。

状态

v0.1 — stdio 传输，Neo4j 5.x 后端，Python ast + tree-sitter（JS/TS/TSX）解析。

Related MCP server: revibe-mcp

快速开始

git clone <codegraph-mcp> && cd codegraph-mcp
uv sync --extra dev              # all deps pinned via uv.lock
docker compose up -d             # Neo4j on bolt://localhost:7687
cp .env.example .env
uv run pytest -m "not slow and not integration"

导入仓库

uv run codegraph ingest https://github.com/<owner>/<name>
# → {"graph_id": "owner/name", "files": 142, "functions": 880, ...}

连接 MCP 主机

Claude Desktop（claude_desktop_config.json）

{
  "mcpServers": {
    "codegraph": {
      "command": "uv",
      "args": ["run", "--directory", "C:\\path\\to\\codegraph-mcp", "codegraph", "serve"]
    }
  }
}

opencode（在 opencode.json 中）

{
  "mcp": {
    "codegraph": {
      "type": "local",
      "command": ["uv", "run", "--directory", "/path/to/codegraph-mcp", "codegraph", "serve"]
    }
  }
}

Cursor（~/.cursor/mcp.json）

{
  "mcpServers": {
    "codegraph": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/codegraph-mcp", "codegraph", "serve"]
    }
  }
}

MCP Inspector（用于在没有 MCP 主机的情况下测试）

uv run mcp dev src/codegraph/server.py

CLI

命令

用途

codegraph ingest <url> [--branch main] [--force]

克隆、解析并将仓库加载到 Neo4j

codegraph serve

运行 MCP 服务器（stdio）——由 MCP 主机启动

codegraph reset --graph-id <owner/name>

从 Neo4j 中硬删除一个仓库（破坏性操作）

codegraph ls

列出已导入的仓库

工具

工具

用途

list_repos

列出已导入的仓库

init_repository_node

确认仓库的图存在；返回文件/函数计数

get_repo_structure

路径下的分层树视图

find_file_dependencies

旗舰功能： 哪些文件/函数依赖于（或被依赖于）某个文件

search_nodes

按名称查找函数/文件

get_node_detail

单个节点的详细信息（行范围、类型）

技术栈

Python 3.11+、mcp>=1.27,<2（稳定的 v1.x FastMCP）、Neo4j 5.x、pydantic v2、tree-sitter、GitPython、pytest、ruff、mypy、uv。

有关架构、约定和测试策略，请参阅 CONTRIBUTING.md。

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • NOMIK

    willFreed1
    F
    license
    Not graded
    quality
    D
    maintenance
    AI-native code intelligence graph that builds a persistent knowledge graph of your codebase in Neo4j and exposes it to AI assistants via MCP, enabling contextual code analysis, impact analysis, and dependency tracking.
    23
    -

  • revibe-mcp

    selvatuple
    A
    license
    A
    quality
    D
    maintenance
    Enables analysis of any GitHub repository to get architecture, file roles, execution flows, system design Q\&A, and structured agent context. Works with MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.
    6
    39 npm
    1
    MIT

  • OpenCodeHub MCP Server

    laithalsaadoon
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides code intelligence for AI coding agents by indexing repositories into a hybrid knowledge graph, enabling agents to query dependencies, impact, and context through 28 MCP tools.
    3
    Apache 2.0

  • codeembed

    robino16
    A
    license
    Not graded
    quality
    C
    maintenance
    Embeds your codebase into a local vector and graph database and exposes it as an MCP tool, enabling AI assistants to perform fast semantic search over your code using Graph RAG.
    4
    MIT