by st3v3nmw
MCP for semantic code search & navigation that reduces token waste
# Add to your Claude Code skills
git clone https://github.com/st3v3nmw/sourcerer-mcpAn 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.
.gitignore files).sourcerer/ to .gitignore: This directory stores the embedded vector databasego install github.com/st3v3nmw/sourcerer-mcp/cmd/sourcerer@latest
brew tap st3v3nmw/tap
brew install st3v3nmw/tap/sourcerer
claude mcp add sourcerer -e OPENAI_API_KEY=your-openai-api-key -e SOURCERER_WORKSPACE_ROOT=$(pwd) -- sourcerer
{
"mcpServers": {
"sourcerer": {
"command": "sourcerer",
"env": {
"OPENAI_API_KEY": "your-openai-api-key",
"SOURCERER_WORKSPACE_ROOT": "/path/to/your/project"
}
}
}
}
Sourcerer 🧙 builds a semantic search index of your codebase:
file.ext::Type::methodfsnotify.gitignore files via git check-ignore.sourcerer/db/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 progressThis approach allows AI agents to find relevant code without reading entire files, dramatically reducing token usage and cognitive load.
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
All contribution...