code-graph-rag — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by vitali87 · MCP Server · ★ 5.2k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is code-graph-rag safe to install? View the security audit →

About code-graph-rag

<img src="https://static.pepy

aiastclaude-codecode-analysiscode-understandingcodebase-searchdeveloper-toolsgraph-databaseknowledge-graphllm

Quick Facts

Stars5,228
Forks699
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score69.9556797990849/100
Open Issues396
Last Updated2026-10-03
Created2025-06-16
Platformsclaude-code, mcp, python
Est. Tokens~23k

Compatible Skills

These tools work well together with code-graph-rag for enhanced workflows:

  • Auditor — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • Nexus-skills — semantic(0.24)+complementary+rare_topics+same_lang+shared_platform (57%)
  • langroid — semantic(0.19)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • axon — semantic(0.35)+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • mcp-server-tree-sitter — semantic(0.34)+rare_topics+same_lang+similar_pop+shared_platform (55%)

code-graph-rag alternative? Top 6 similar tools

Looking for a code-graph-rag alternative? If you're comparing code-graph-rag with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • antigravity-workspace-template by study8677 · ⭐ 1.3k

    Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi

  • jcodemunch-mcp by jgravelle · ⭐ 2.7k

    Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retr

  • m_flow by FlowElement-ai · ⭐ 2.4k

    A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

  • nocturne_memory by Dataojitori · ⭐ 1.4k

    A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and

  • ai-guide by liyupi · ⭐ 20.6k

    程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享 OpenClaw 保姆级教程、大模型玩法(DeepSeek / GPT / Gemini / Claude / GLM)、最新 AI 资讯、Pr

  • klavis by Klavis-AI · ⭐ 5.8k

    Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is code-graph-rag?

code-graph-rag is The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs. It is categorized as a MCP Server with 5.2k GitHub stars.

What programming language is code-graph-rag written in?

code-graph-rag is primarily written in Python. It covers topics such as ai, ast, claude-code.

How do I install or use code-graph-rag?

You can find installation instructions and usage details in the code-graph-rag GitHub repository at github.com/vitali87/code-graph-rag. The project has 5.2k stars and 699 forks, indicating an active community.

What license does code-graph-rag use?

code-graph-rag is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to code-graph-rag?

The top alternatives to code-graph-rag on Agent Skills Hub include antigravity-workspace-template, jcodemunch-mcp, m_flow. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools