Delegate deep repository analysis to the Gemini CLI
Gemini Researcher
A lightweight, stateless MCP (Model Context Protocol) server that lets developer agents (Claude Code, GitHub Copilot) delegate deep repository analysis to the Gemini CLI. The server is read-only, returns structured JSON (as text content), and is optimized to reduce the calling agent's context and model usage.
Status: v1 complete. Core features are stable, but still early days. Feedback welcome!
If this project extended the lifespan of your usage window, ⭐ please consider giving it a star! :)
Primary goals:
- Reduce agent context usage by letting Gemini CLI read large codebases locally and do its own research
- Reduce calling-agent model usage by offloading heavy analysis to Gemini
- Keep the server stateless and read-only for safety
Why use this?
Instead of copying entire files into your agent's context (burning tokens and cluttering the conversation), this server lets Gemini CLI read files directly from your project. Your agent sends a research query, Gemini does the heavy lifting with its large context window, and returns structured results. You save tokens, your agent stays focused, and complex codebase analysis becomes practical.
Verified clients: Claude Code, Cursor, VS Code (GitHub Copilot)
[!NOTE] It definitely works with other clients, but I haven't personally tested them yet. Please open an issue if you try it elsewhere!
Table of contents
Overview
Gemini Researcher accepts research-style queries over the MCP protocol and spawns the Gemini CLI in headless, read-only mode to perform large-context analysis on local files referenced with @path. Results are returned as pretty-printed JSON strings suitable for programmatic consumption by agent clients.
Prerequisites
- Node.js 18+ installed
- Gemini CLI installed:
npm install -g @google/gemini-cli - Gemini CLI authenticated (recommended:
gemini→ Login with Google) or setGEMINI_API_KEY
Quick checks:
node --version
gemini --version
Quickstart
Step 1: Validate environment
Run the setup wizard to verify Gemini CLI is installed and authenticated:
npx gemini-researcher init
Step 2: Configure your MCP client
Standard config works in most of the tools:
{
"mcpServers": {
"gemini-researcher": {
"command": "npx",
"args": [
"gemini-researcher"
]
}
}
}
VS Code
Add to your VS Code MCP settings (create .vscode/mcp.json if needed):
{
"servers": {
"gemini-researcher": {
"command": "npx",
"args": [
"gemini-researcher"
]
}
}
}
Claude Code
Option 1: Command line (recommended)
Local (user-wide) scope
# Add the MCP server via CLI
claude mcp add --transport stdio gemini-researcher -- npx gemini-researcher
# Verify it was added
claude mcp list
Project scope
Navigate to your project directory, then run:
# Add the MCP server via CLI
claude mcp add --scope project --transport stdio gemini-researcher -- npx gemini-researcher
# Verify it was added
claude mcp list
Option 2: Manual configuration
Add to .mcp.json in your project root (project scope):
{
"mcpServers": {
"gemini-researcher": {
"command": "npx",
"args": [
"gemini-researcher"
]
}
}
}
Or add to ~/.claude/settings.json for local scope.
After adding the server, restart Claude Code and use /mcp to verify the connection.
Cursor
Go to Cursor Settings -> Tools & MCP -> Add a Custom MCP Server. Add the following configuration:
{
"mcpServers": {
"gemini-researcher": {
"type": "stdio",
"command": "npx",
"args
Tools (1)
researchAccepts research-style queries and spawns the Gemini CLI in headless, read-only mode to perform large-context analysis on local files.Environment Variables
GEMINI_API_KEYAPI key for Gemini authentication if not using the interactive loginConfiguration
{
"mcpServers": {
"gemini-researcher": {
"command": "npx",
"args": [
"gemini-researcher"
]
}
}
}