srclight/srclight
by Various
Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerate
MCP
srclight/srclight
Added 1 June 2026
Overview
A deep code indexing MCP server for AI agents. It provides 25 tools including hybrid FTS5 and embedding search, call graphs, git blame/hotspots, and build system analysis. It supports multi-repo workspaces, GPU-accelerated semantic search, and 10 languages via tree-sitter, all fully local with no cloud dependencies.
Best for
Best for
Developers and AI agent builders who need a local, privacy-preserving code indexing server
Use cases
- Enabling AI agents to navigate and understand large codebases
- Performing semantic code search with GPU acceleration
- Analyzing build systems and git history for hotspots
How to use
Install
pip install srclight Tested with
Claude Code, Cursor, Claude Desktop, ChatGPT
Notes
A deep code indexing MCP server for AI agents. It provides 25 tools including hybrid FTS5 and embedding search, call graphs, git blame/hotspots, and build system analysis. It supports multi-repo workspaces, GPU-accelerated semantic search, and 10 languages via tree-sitter, all fully local with no cloud dependencies.
44 stars on GitHub. Last updated 2026-04-27. Licensed MIT.
Use cases
- Enabling AI agents to navigate and understand large codebases
- Performing semantic code search with GPU acceleration
- Analyzing build systems and git history for hotspots
Pros
- Fully local with no cloud dependencies ensures privacy and offline use
- Wide range of tools from search to call graphs and git analysis
- GPU-accelerated semantic search for fast code retrieval
Cons
- Small community and limited adoption may mean fewer resources
- GPU acceleration required for optimal performance, not available on all setups
- Language support limited to 10 languages via tree-sitter
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Fully local with no cloud dependencies ensures privacy and offline use
- Wide range of tools from search to call graphs and git analysis
- GPU-accelerated semantic search for fast code retrieval
Cons
- Small community and limited adoption may mean fewer resources
- GPU acceleration required for optimal performance, not available on all setups
- Language support limited to 10 languages via tree-sitter
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Aider
Paul Gauthier
Terminal-first AI pair programmer. Edits files in your repo, commits with sensible messages, runs your tests.
Cline
Cline
Open-source autonomous coding agent that lives inside VS Code. BYO model key, watch it work.
Continue
Continue.dev
Open-source AI code assistant for VS Code and JetBrains. Customisable, BYO model, built for enterprise.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.