为AI代理提供深度代码索引MCP服务器。25个工具：混合FTS5 + 嵌入搜索、呼叫图、git blame/hotspots、构建系统分析。
概览
SQLite FTS5 + 树置 + 嵌入 + MCP。 Srclight 构建了一个丰富且可搜索的代码库索引，AI 编码代理可以即时查询——用精确、结构化的查找替代数十次 grep/glob 调用。它是目前最全面的代码智能 MCP 服务器：42 个工具，涵盖符号搜索、关系图、社区检测、影响分析、git 变更智能、语义搜索、构建系统意识和文档提取——这些能力是其他 MCP 服务器无法兼备的。完全本地化且私密：你的代码永远不会离开你的机器。 AI编码代理（Claude代码、光标等）花费了大量时间——搜索文件、阅读代码以理解结构、寻找调用者和被调用者。Srclight消除了这些浪费。
概述（AI 翻译）
AI代理的深度代码索引。 SQLite FTS5 + 树置 + 嵌入 + MCP。
Srclight 构建了一个丰富且可搜索的代码库索引，AI 编码代理可以即时查询——用精确、结构化的查找替代数十次 grep/glob 调用。它是目前最全面的代码智能 MCP 服务器：42 个工具，涵盖符号搜索、关系图、社区检测、影响分析、git 变更智能、语义搜索、构建系统意识和文档提取——这些能力是其他 MCP 服务器无法兼备的。完全本地化且私密：你的代码永远不会离开你的机器。
为什么？
AI编码代理（Claude Code、Cursor等）花费了**40-60%的令牌用于定位——搜索文件、阅读代码理解结构、寻找调用者和被调用者。Srclight消除了这些浪费。
| 没有Srclight | 带Srclight |
|---|---|
| 8-12发grep弹搜索来电者 | get_callers("lookup") — 一通电话 |
| 阅读5个文件以理解模块 | codebase_map() — 即时概述 |
| “找到能做X的代码” →20次 grep | semantic_search("dictionary lookup") — 一个呼叫 |
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
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, JavaScript, TypeScript, PHP, Lua, Bash, SQL, Groovy, CMake, Markdown — include fragments (
.inc,.inl,.ipp,.tcc) included, plus any extension you declare with--ext - Says what it skipped —
index_statusnames the extensions a run walked past, so an incomplete answer never reads as a complete one - 10 document formats — PDF, DOCX, XLSX, HTML, CSV/TSV, email (.eml), images (PNG/JPG/SVG/etc.), plain text, RST, Markdown
- Optional OCR — PaddleOCR for scanned/image-only PDF pages; pytesseract for images
- 4 search modes — symbol names, source code (trigram), documentation (stemmed), semantic (embeddings)
- Hybrid search — RRF fusion of keyword + semantic results for best accuracy
- Multi-repo workspaces — search across all your repos simultaneously via SQLite ATTACH+UNION
- MCP server — works with Claude Code, Cursor, and any MCP client
- CLI — index, search, and inspect from the terminal
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"srclight": {
"command": "srclight",
"args": ["serve", "--workspace", "myworkspace"]
}
}
}