Deep code indexing MCP server for AI agents with hybrid FTS5 + embedding search, call graphs, and multi-repo workspaces.
srclight is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view srclight/srclight --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Srclight is a tool that indexes your codebase so AI coding agents can search it instantly. It understands code structure, finds function callers, and performs semantic searches without sending your code anywhere. It works fully offline and supports many programming languages.
Srclight is a comprehensive code intelligence MCP server that builds a rich, searchable index of your codebase. It replaces dozens of grep/glob calls with precise, structured lookups. Key features include: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis, multi-repo workspaces, GPU-accelerated semantic search, and support for 11 programming languages via tree-sitter. It is fully local with zero cloud dependencies, ensuring your code never leaves your machine. The server provides 42 tools covering symbol search, relationship graphs, community detection, impact analysis, git change intelligence, semantic search, build system awareness, and document extraction. It supports incremental indexing, auto-reindex via git hooks, and optional OCR for scanned documents.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 91 days ago.
45 GitHub stars indicate community interest.
5 open issues signal maintenance load.
MIT license detected.
AI coding agents can instantly find function definitions and callers without multiple grep rounds.
Developers can perform semantic searches across multiple repositories to find relevant code.
Impact analysis before refactoring: detect all callers and dependencies of a function.
Git change intelligence: understand blast radius of changes before committing.
Offline code search in air-gapped environments with local embeddings.
No data leaves your machine; fully local and private.
Requires Python 3.11+ and optional dependencies for OCR and GPU acceleration.
Semantic search requires Ollama running locally for embeddings.
45
Stars
9
Forks
5
Issues
MIT
License
A project template that turns your repository into stable infrastructure for AI-assisted development.
Local code intelligence MCP server and CLI for AI coding agents, providing semantic search and call graph analysis.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
Deep code indexing MCP server for AI agents with hybrid FTS5 + embedding search, call graphs, and multi-repo workspaces.
AI coding agent users (Claude Code, Cursor, etc.) who want to reduce token waste on code orientation., Developers working on large codebases who need fast, precise code search., Security-conscious teams that require fully local, private code indexing.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
No data leaves your machine; fully local and private. Requires Python 3.11+ and optional dependencies for OCR and GPU acceleration.
Similar or complementary options to evaluate include attractor-guided-engineering-template, codanna, context7.
Jun 7, 2026
3 security/trust notes recorded.
Setup difficulty is 3/5.