Grepai Mcp Tools

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.

skills.sh installs: 744
GitHub stars: 20
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yoanbernabeu/grepai-skills --skill grepai-mcp-tools --agent claude-code

Installs into .claude/skills of the current project.

Files

GrepAI MCP Tools Reference

This skill provides a complete reference for all tools available through GrepAI's MCP server.

When to Use This Skill

Understanding available MCP tools
Learning tool parameters and options
Integrating GrepAI with AI assistants
Debugging MCP tool usage

Starting the MCP Server

grepai mcp-serve

The server exposes tools via the Model Context Protocol.

Available Tools

1. grepai_search

Semantic code search using embeddings.

Parameters

Parameter	Type	Required	Default	Description
`query`	string	Yes	-	Search query describing what to find
`limit`	number	No	10	Maximum results to return
`compact`	boolean	No	false	Return compact output (no content)
`format`	string	No	"json"	Output format: "json" or "toon" (v0.26.0+)

Example Request

{
  "tool": "grepai_search",
  "parameters": {
    "query": "user authentication middleware",
    "limit": 5,
    "compact": true,
    "format": "toon"
  }
}