codegraph-mcp
codegraph-mcp
GitHub 저장소용 지식 그래프 MCP 서버입니다. 모든 GitHub 저장소의 코드를 Neo4j 그래프(Repository / File / Function 노드; CONTAINS / DEFINES / IMPORTS / CALLS 엣지)로 수집하고, 해당 그래프를 읽기 전용 MCP 도구로 Claude Desktop, opencode, Cursor 또는 Model Context Protocol을 지원하는 모든 MCP 호스트에 제공합니다.
상태
v0.1 — stdio 전송, Neo4j 5.x 백엔드, Python ast + tree-sitter (JS/TS/TSX) 파싱.
Related MCP server: NOMIK
빠른 시작
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"저장소 수집
uv run codegraph ingest https://github.com/<owner>/<name>
# → {"graph_id": "owner/name", "files": 142, "functions": 880, ...}MCP 호스트 연결
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"codegraph": {
"command": "uv",
"args": ["run", "--directory", "C:\\path\\to\\codegraph-mcp", "codegraph", "serve"]
}
}
}opencode (opencode.json)
{
"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 (MCP 호스트 없이 테스트용)
uv run mcp dev src/codegraph/server.pyCLI
명령어 | 목적 |
| 저장소를 클론하고 파싱하여 Neo4j에 로드 |
| MCP 서버 실행 (stdio) — MCP 호스트가 실행 |
| Neo4j에서 저장소 하나를 완전히 삭제 (파괴적 작업) |
| 수집된 저장소 목록 조회 |
도구
도구 | 목적 |
| 수집된 저장소 목록 조회 |
| 저장소 그래프 존재 확인; 파일/함수 개수 반환 |
| 경로 아래 계층적 트리 보기 |
| 핵심 도구: 파일/함수가 의존하거나 의존받는 대상 조회 |
| 이름으로 함수/파일 검색 |
| 단일 노드의 상세 정보 (코드 라인 범위, 종류) |
기술 스택
Python 3.11+, mcp>=1.27,<2 (안정적인 v1.x FastMCP), Neo4j 5.x, pydantic v2, tree-sitter, GitPython, pytest, ruff, mypy, uv.
아키텍처, 규칙 및 테스트 전략은 CONTRIBUTING.md를 참조하세요.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityCmaintenanceTransforms code repositories and development documentation into a queryable Neo4j knowledge graph, enabling AI assistants to perform intelligent code analysis, dependency mapping, impact assessment, and automated documentation generation across 15+ programming languages.7
- Flicense-qualityDmaintenanceAI-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.21
- AlicenseAqualityDmaintenanceEnables 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.639MIT
- Alicense-qualityAmaintenanceProvides 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.3Apache 2.0
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
Repo intel for AI coding agents: overview, PRs, contributors, hot files, CI, deps. Remote MCP.
Knowledge coverage map and health score. Ingest docs into a governed knowledge graph via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ritesh-977/codegraph-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server