Sourcerer MCP
st3v3nmw/sourcerer-mcp
Busca semântica em código com vetores, economia de tokens para IA
Ver no GitHubServidor MCP para busca semântica e navegação eficiente em codebases usando embeddings vetoriais. Permite que agentes IA encontrem funções, classes e trechos de código relevantes sem ler arquivos inteiros, reduzindo drasticamente o consumo de tokens.
Instalação
npx convez-ai st3v3nmw/sourcerer-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Agentes IA navegando grandes codebases sem overhead de tokens
- Desenvolvimento assistido por IA com context window otimizado
- Refatoração e análise de código semantic-aware
- Integração em fluxos de desenvolvimento com Claude
Veredito

Ferramenta bem arquitetada que resolve um problema real: consumo excessivo de tokens ao processar codebases grandes. Implementação sólida em Go com suporte a múltiplas linguagens via Tree-sitter, embora dependência de OpenAI API e falta de embeddings locais ainda sejam limitações.
README
A tradução para o português deste README ainda está na fila.
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
.gitignorefiles) - 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 format:
file.ext::Type::method
2. File System Integration
- Watches for file changes using
fsnotify - Respects
.gitignorefiles viagit 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 relevant code using semantic searchget_chunk_code: Retrieve specific chunks by IDfind_similar_chunks: Find similar chunksindex_workspace: Manually trigger re-indexingget_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, JavaScript, Markdown, Python, TypeScript
Planned: C, C++, Java, Ruby, Rust, and others
Contributing
All contributions welcome! See CONTRIBUTING.md.
$ ls @stephenmwangi.com
- gh:st3v3nmw/obsidian-spaced-repetition
- gh:st3v3nmw/lsfr