Srclight — AI skill for Claude Code
Deep code indexing MCP server for AI agents.
How to install Srclight
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open vishalhabib99/srclight and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Srclight does
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-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.
Alternatives in AI
- Claude Squad — by smtg-ai - Claude Squad is a terminal app that manages multiple Claude Code, Codex (and other local agents i 6.5k ★
- Rust Skills — Rust Developer AI Assistance System — Meta-Problem-Driven Knowledge Indexing 893 ★
- Codeseek — Rust-powered code intelligence CLI for AI coding agents 764 ★
README
Srclight
[](https://pypi.org/project/srclight/) [](https://github.com/srclight/srclight/blob/master/LICENSE) [](https://pypi.org/project/srclight/)
**Deep code indexing for AI agents.** SQLite FTS5 + tree-sitter + embeddings + MCP.
Srclight builds a rich, searchable index of your codebase that AI coding agents can query instantly — replacing dozens of grep/glob calls with precise, structured lookups. It is the most comprehensive code intelligence MCP server available: 42 tools covering symbol search, relationship graphs, community detection, impact analysis, git change intelligence, semantic search, build system awareness, and document extraction — capabilities no other single MCP server combines. Fully local and private: your code never leaves your machine.
Why?
AI coding agents (Claude Code, Cursor, etc.) spend **40-60% of their tokens on orientation** — searching for files, reading code to understand structure, hunting for callers and callees. Srclight eliminates this waste.
| Without Srclight | With Srclight |
|---|---|
| 8-12 grep rounds to find callers | get_callers("lookup") — one call |
| Read 5 files to understand module | codebase_map() — instant overview |
| "Find code that does X" → 20 greps | semantic_search("dictionary lookup") — one call |
| Edit a function, break 47 callers | detect_changes() — shows blast radius before you commit |
| 15-25 tool calls per bug fix | 5-8 tool calls per bug fix |
Features
- Minimal dependencies — single SQLite file per repo, no Docker/Redis/vector DB
- Fully offline — no API calls, works air-gapped (Ollama local embeddings)
- Incremental — only re-indexes changed files (content hash detection)
- 19 languages — Python, C, C++, C#, Java, Kotlin, Swift, Dart, Go, Rust
Related Skills
Brain CLI
Persistent memory for AI agents and personal knowledge management. Single-file Python CLI: hybrid semantic + k
Doc Search MCP
Local MCP server that indexes PDFs, EPUBs, HTML, Markdown and text files and makes them searchable by LLM codi
Octocode
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
Pebrel
AI-native, GPU-accelerated terminal emulator for Windows with SSH, persistent sessions, split panes, and first
Nebula
AI-native, GPU-accelerated terminal emulator for Windows with SSH, persistent sessions, split panes, and first
Peridot
Peridot v1.6.0 [STABLE] Sovereign AI Kernel. Offline, GPU accelerated Qwen framework: a 27B model fully on an
Related Agents
Python RAG Backend Engineer
Production-grade Python RAG backend engineer specializing in ChromaDB vector storage, sentence-transformers em
Local Brain Search
Local vector search and connection discovery for the Brain. Use for semantic search, finding connections betwe
Vector Store Indexer
MUST BE USED PROACTIVELY for indexing and semantic search across the file system. This agent creates vector em