Sourcerer MCP

Sourcerer MCP 🧙

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

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

Installation

Go

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

Homebrew

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

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:

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

This approach allows AI agents to find relevant code without reading entire files, dramatically reducing token usage and cognitive load.

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

Contributing

All contributions welcome!

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

local-only server

The server can only run on the client's local machine because it depends on local resources.

Related MCP Servers

Kodit
helixml
-
security
A
license
-
quality
A Code Indexing MCP Server that connects AI coding assistants to external codebases, providing accurate and up-to-date code snippets to reduce mistakes and hallucinations.
Last updated -
75
Python
Apache 2.0
Rules MCP Server
markacianfrani
A
security
F
license
A
quality
An MCP server that allows coding agents to look up contextual rules and patterns on demand, providing just-in-time guidance for specific tasks like writing tests or authoring UI.
Last updated -
2
9
TypeScript
AI Agent Template MCP Server
bswa006
A
security
F
license
A
quality
An MCP server that enhances AI agents' coding capabilities by providing zero hallucinations, improved code quality, security-first approach, high test coverage, and efficient context management.
Last updated -
15
186
1
TypeScript
MCP Tools
flesler
A
security
A
license
A
quality
A comprehensive MCP server providing tools for AI agents to interact with code, including reading symbols, importing modules, replacing text, and sending OS notifications.
Last updated -
3
51
2
TypeScript
MIT License

View all related MCP servers