This is a reference guide for GrepAI's MCP server tools, which let AI assistants do semantic code search and call graph analysis on your codebase. You get five tools: search by natural language queries, trace callers and callees of any function, build complete call graphs, and check index status. The compact output format cuts token usage by 80%, which matters when you're running repeated searches through an AI chat session. Main use case is hooking up Claude or another assistant to explore unfamiliar codebases without manually grepping around. You'll need to run `grepai watch` first to build the index, and it requires Ollama or another embedder running locally. Responses come back as JSON with file paths, line numbers, and similarity scores.
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-mcp-tools