Enterprise DNA
M MCP Servers Developer low

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

S

MCP

srclight/srclight

Added 1 June 2026

#code-indexing #code-intelligence #code-search #developer-tools #embeddings #fts5 #mcp #mcp-server

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
Free 27-page guide

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.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks