Local Code Search
Local Code Indexing for Cursor provides a Python-based server that locally indexes codebases using ChromaDB and enables semantic code search through the MCP protocol. Built with FastMCP, it watches specified project directories, automatically indexes code files using language-specific parsers, and maintains a vector database of code chunks that can be queried using natural language. The implementation includes Docker containerization for easy deployment, file system watchers for real-time updates, and configurable ignore patterns for directories and files. This tool is particularly valuable for developers who want to perform semantic code search within their projects directly through the Cursor IDE without sending their code to external services.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Local Code Search from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.