# Codebase Memory MCP — Code Intelligence for AI Agents

> High-performance code intelligence MCP server. Indexes repos in milliseconds via tree-sitter AST, supports 66 languages, sub-ms graph queries. MIT, 1,300+ stars.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

Add to your `.mcp.json` (Claude Code) or MCP client config:
```json
{
  "mcpServers": {
    "codebase-memory-mcp": {
      "command": "/path/to/codebase-memory-mcp",
      "args": []
    }
  }
}
```

Download the binary from [GitHub Releases](https://github.com/DeusData/codebase-memory-mcp/releases), then restart Claude Code.

---

## Intro

Codebase Memory MCP is the fastest code intelligence engine for AI coding agents, with 1,300+ GitHub stars. It full-indexes an average repository in milliseconds and can index the Linux kernel (28M lines, 75K files) in 3 minutes. Uses tree-sitter AST parsing across 66 languages with sub-millisecond graph queries. Best for developers using Claude Code, Cursor, or any MCP client who want their AI to deeply understand their codebase. Works with JavaScript, Python, Go, Rust, Java, C++, and 60+ more languages.

Explore more MCP servers on [TokRepo MCP Hub](https://tokrepo.com/en/@MCP%20Hub).

---

## Codebase Memory MCP — Full Code Intelligence Engine

### How It Works

Codebase Memory MCP parses your entire codebase using tree-sitter AST grammars and builds a persistent knowledge graph stored in SQLite. AI agents query this graph via 14 MCP tools to understand code structure, trace dependencies, and find patterns.

### Key Features

- **66 language support** — vendored tree-sitter grammars for JS, Python, Go, Rust, Java, C++, and more
- **Sub-millisecond queries** — SQLite-backed graph with Cypher-like query support
- **14 MCP tools** — search, tracing, architecture analysis, dead code detection
- **3D graph visualization** — built-in UI to explore code relationships
- **Git diff impact mapping** — understand how changes affect the codebase
- **Cross-service HTTP route linking** — maps API routes across microservices
- **ADR management** — Architecture Decision Records tracking
- **Background file watcher** — auto-sync when files change
- **Single static binary** — zero dependencies, just download and run

### Performance Benchmarks

| Codebase | Files | Lines | Index Time |
|----------|-------|-------|------------|
| Average repo | ~500 | ~50K | < 1 second |
| Large monorepo | ~5,000 | ~500K | ~30 seconds |
| Linux kernel | 75,000 | 28M | ~3 minutes |

### MCP Tools Available

1. **search** — find functions, classes, variables by name or pattern
2. **trace** — follow call chains and dependency paths
3. **architecture** — get high-level module overview
4. **dead-code** — detect unused functions and imports
5. **impact** — analyze which code is affected by a change
6. **routes** — map HTTP endpoints across services
7. And 8 more specialized analysis tools

### Installation

Download the single binary from GitHub Releases:
```bash
# Download latest release (check GitHub for your platform)
curl -LO https://github.com/DeusData/codebase-memory-mcp/releases/latest/download/codebase-memory-mcp-linux-amd64
chmod +x codebase-memory-mcp-linux-amd64
mv codebase-memory-mcp-linux-amd64 /usr/local/bin/codebase-memory-mcp
```

### FAQ

**Q: What is Codebase Memory MCP?**
A: A high-performance MCP server that indexes your entire codebase into a queryable knowledge graph, giving AI agents deep code understanding with sub-millisecond response times.

**Q: Is Codebase Memory MCP free?**
A: Yes, fully open-source under the MIT license.

**Q: How many programming languages does it support?**
A: 66 languages via vendored tree-sitter grammars, covering all major languages including JavaScript, Python, Go, Rust, Java, C++, TypeScript, Ruby, and more.

---

## Source & Thanks

> Created by [DeusData](https://github.com/DeusData). Licensed under MIT.
>
> [codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp) — ⭐ 1,300+

Thanks to the DeusData team for building the fastest code intelligence engine for MCP.

---

<!-- ZH -->

## 快速使用

添加到你的 `.mcp.json`（Claude Code）或 MCP 客户端配置：
```json
{
  "mcpServers": {
    "codebase-memory-mcp": {
      "command": "/path/to/codebase-memory-mcp",
      "args": []
    }
  }
}
```

从 [GitHub Releases](https://github.com/DeusData/codebase-memory-mcp/releases) 下载二进制文件，重启 Claude Code 即可。

---

## 简介

Codebase Memory MCP 是 AI 编码 Agent 最快的代码智能引擎，GitHub 1,300+ star。普通仓库毫秒级全量索引，Linux 内核（2800 万行、7.5 万文件）3 分钟完成。基于 tree-sitter AST 解析，支持 66 种编程语言，亚毫秒级图查询。适合使用 Claude Code、Cursor 等 MCP 客户端的开发者。

---

## Codebase Memory MCP — 全量代码智能引擎

### 核心特性

- **66 种语言** — JS、Python、Go、Rust、Java、C++ 等
- **亚毫秒查询** — SQLite 支撑的知识图谱
- **14 个 MCP 工具** — 搜索、追踪、架构分析、死代码检测
- **3D 图可视化** — 内置 UI 探索代码关系
- **Git diff 影响分析** — 理解代码变更影响范围
- **单文件二进制** — 零依赖，下载即用

### 性能基准

| 代码库 | 文件数 | 行数 | 索引时间 |
|--------|--------|------|----------|
| 普通项目 | ~500 | ~5 万 | < 1 秒 |
| 大型单体仓库 | ~5,000 | ~50 万 | ~30 秒 |
| Linux 内核 | 75,000 | 2800 万 | ~3 分钟 |

### FAQ

**Q: Codebase Memory MCP 是什么？**
A: 一个高性能 MCP 服务器，将整个代码库索引为可查询的知识图谱，让 AI Agent 深度理解代码结构。

**Q: 免费吗？**
A: 完全免费开源，MIT 许可。

---

## 来源与感谢

> Created by [DeusData](https://github.com/DeusData). Licensed under MIT.
>
> [codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp) — ⭐ 1,300+


---
Source: https://tokrepo.com/en/workflows/a3fe5165-33ca-11f1-9bc6-00163e2b0d79
Author: MCP Hub