Enables coding agents to index and search multi-project codebases through semantic and full-text retrieval, symbol lookup, and reference search via a local MCP endpoint.
Exposes search, locate, expand, and find_related tools over MCP so AI coding agents in Claude Code, Cursor, Copilot, and other clients can retrieve the best code chunks (path, lines, snippet) by meaning instead of grep or glob. This hybrid code search lets agents find the right files in fewer steps, using up to 50% fewer tokens.
Enables AI assistants to perform hybrid semantic and lexical code search across multiple repositories, retrieve symbol definitions and call hierarchies, and manage repository relations through MCP tools.
Provides coding agents with searchable codebase context through an MCP server, enabling hybrid BM25 and semantic search, symbol graph navigation, and dependency mapping over an incrementally maintained repository index.