Sourcerer MCP

🚀 Sourcerer MCP 🧙

An MCP server for semantic code search & navigation that enables AI agents to work efficiently without exhausting costly tokens. Instead of reading entire files, agents can perform conceptual searches and directly jump to the specific functions, classes, and code chunks they need.

🚀 Quick Start

Sourcerer MCP is an innovative tool that streamlines the process of code search and navigation for AI agents. It allows agents to quickly locate the code they need without having to read through entire files, saving both tokens and cognitive load.

✨ Features

• Semantic Code Search: Enables conceptual searches, allowing AI agents to find relevant code based on functionality rather than just text matching.
• Code Chunking: Parses source files into meaningful chunks (functions, classes, methods, types) with stable IDs for easy navigation.
• File System Integration: Monitors file changes, respects .gitignore files, and automatically re - indexes changed files.
• Vector Database: Uses a persistent vector storage system to store code embeddings for semantic similarity searches.
• MCP Tools: Provides a set of tools for semantic search, retrieving source code, triggering re - indexing, and checking indexing status.

📦 Installation

Go

go install github.com/st3v3nmw/sourcerer-mcp/cmd/sourcerer@latest

Homebrew

brew tap st3v3nmw/tap
brew install st3v3nmw/tap/sourcerer

📚 Documentation

Configuration

Claude Code

claude mcp add sourcerer -e OPENAI_API_KEY=your-openai-api-key -e SOURCERER_WORKSPACE_ROOT=$(pwd) -- sourcerer

mcp.json

{
  "mcpServers": {
    "sourcerer": {
      "command": "sourcerer",
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key",
        "SOURCERER_WORKSPACE_ROOT": "/path/to/your/project"
      }
    }
  }
}

How it Works

Sourcerer builds a semantic search index of your codebase through the following steps:

1. Code Parsing & Chunking

• Uses Tree-sitter to parse source files into ASTs.
• Extracts meaningful chunks (functions, classes, methods, types) with stable IDs.
• Each chunk includes source code, location info, and contextual summaries.
• Chunk IDs follow the pattern: file.ext::TypeName::methodName.

2. File System Integration

• Watches for file changes using fsnotify.
• Respects .gitignore files via git check-ignore.
• Automatically re-indexes changed files.
• Stores metadata to track modification times.

3. Vector Database

• Uses chromem-go for persistent vector storage in .sourcerer/db/.
• Generates embeddings via OpenAI's API for semantic similarity.
• Enables conceptual search rather than just text matching.
• Maintains chunks, their embeddings, and metadata.

4. MCP Tools

• semantic_search: Find code by concept/functionality.
• get_source_code: Retrieve specific chunks by ID.
• index_workspace: Manually trigger re-indexing.
• get_index_status: Check indexing progress.

🔧 Technical Details

Supported Languages

Language support requires writing Tree-sitter queries to identify functions, classes, interfaces, and other code structures for each language.

• Supported: Go
• Planned: Python, TypeScript, JavaScript

📄 License

No license information provided in the original document.

Demo

Requirements

• OpenAI API Key: Required for generating embeddings (local embedding support planned).
• Git: Must be a git repository (respects .gitignore files).
• Add .sourcerer/ to .gitignore: This directory stores the embedded vector database.

Contributing

All contributions welcome!