capybearista avatar

Gemini Researcher

capybearista/gemini-researcher

This server routes deep codebase analysis queries from Claude or Copilot to the Gemini CLI, which reads your project files directly instead of stuffing them into your agent's context window. It exposes five main tools: quick_query for fast answers using Flash, deep_research for architecture or security audits with Pro, analyze_directory for mapping unfamiliar repos, validate_paths to pre-check files, and health_check for diagnostics. All responses come back as structured JSON, chunked if large. The server enforces a read-only admin policy by default so Gemini can't modify files or run shell commands. Particularly useful when you need to analyze sprawling codebases without burning thousands of tokens copying files into context.

tools
6
auth
Secret needed
transport
STDIO
env vars
8
last updated
Jan 26, 2026

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

quick_queryFast analysis with flash model

Fast analysis with flash model

No parameter schema in public metadata yet.

deep_researchIn-depth analysis with pro model

In-depth analysis with pro model

No parameter schema in public metadata yet.

analyze_directoryMap directory structure

Map directory structure

No parameter schema in public metadata yet.

validate_pathsPre-check file paths

Pre-check file paths

No parameter schema in public metadata yet.

health_checkDiagnostics

Diagnostics

No parameter schema in public metadata yet.

fetch_chunkGet chunked responses

Get chunked responses

No parameter schema in public metadata yet.

Sponsors

Configuration

GEMINI_API_KEYsecret

Gemini API key (optional if you already authenticated Gemini CLI via "gemini" login)

PROJECT_ROOT

Override the project root directory used for path validation (defaults to current working directory)

RESPONSE_CHUNK_SIZE_KB

Chunk size threshold (KB) for large responses (default: 10)

CACHE_TTL_MS

Chunk cache TTL in milliseconds (default: 3600000 / 1 hour)

DEBUG

Enable debug logging (set to "true" or "1")

GOOGLE_APPLICATION_CREDENTIALS

Vertex AI / Google auth: path to a service account JSON credentials file

GOOGLE_CLOUD_PROJECT

Vertex AI / Google auth: GCP project ID (used by some auth configurations)

VERTEX_AI_PROJECT

Vertex AI / Google auth: Vertex AI project identifier (used by some auth configurations)

Readme

Gemini Researcher

NPM Version NPM Downloads License: BSD-3 Claude

badge

A lightweight, stateless MCP (Model Context Protocol) server that lets developer agents (Claude Code, GitHub Copilot) hand off deep repository analysis to the Gemini CLI. The server is read-only, returns structured JSON (as text content), and is designed 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 saved you tokens, ⭐ please consider giving it a star! :)


View the full README on GitHub

Details

Repository
github.com/capybearista/gemini-researcher
Category
AI & LLM Tools
Package
gemini-researcher
Transport
STDIO
Auth
Required
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1tekgnosis avatarGnosis Memorytekgnosis/gnosismemoryPersistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.0stars
2flsteven87 avatarLlm Wiki Mcpflsteven87/llm-wiki-mcpMCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.0stars
3agenson-tools avatarAgent Output Guardagenson-tools/agent-output-guard-mcpValidate and verify data from other agents before acting on it. Zero LLM costs.0stars
4br0ski777 avatarVector Search APIbr0ski777/vector-search-x402In-memory vector search with TF-IDF and cosine similarity. x402 micropayment.0stars
5marras0914 avatarAgent Toolbelt Mcpmarras0914/agent-toolbelt19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.0stars
6mdfifty50-boop avatarAgent Costcentermdfifty50-boop/agent-costcenter-mcpMulti-agent billing and cost allocation tracking0stars