gemini-researcher

Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage

stdio v1.0.2

Connection Configuration

Add this to your AI agent's MCP config file to connect.

Run in your terminal:

claude mcp add io.github.capybearista--gemini-researcher -- npx

Transport

stdio

Authentication

None

Version

v1.0.2

Server Name

io.github.capyBearista/gemini-researcher

Last Updated

Jan 26, 2026

How to install and connect this MCP server.

Environment variables you must provide when running this server.

Variable	Description	Required
`GEMINI_API_KEY` secret	Gemini API key (optional if you already authenticated Gemini CLI via "gemini" login)	Optional
`PROJECT_ROOT`	Override the project root directory used for path validation (defaults to current working directory)	Optional
`RESPONSE_CHUNK_SIZE_KB`	Chunk size threshold (KB) for large responses (default: 10)	Optional
`CACHE_TTL_MS`	Chunk cache TTL in milliseconds (default: 3600000 / 1 hour)	Optional
`DEBUG`	Enable debug logging (set to "true" or "1")	Optional
`GOOGLE_APPLICATION_CREDENTIALS`	Vertex AI / Google auth: path to a service account JSON credentials file	Optional
`GOOGLE_CLOUD_PROJECT`	Vertex AI / Google auth: GCP project ID (used by some auth configurations)	Optional
`VERTEX_AI_PROJECT`	Vertex AI / Google auth: Vertex AI project identifier (used by some auth configurations)	Optional