HotStack

← Back to browse

gemini-researcher

Indexed by io.github.capyBearista
View source ↗

About

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

Use this server

Add it to your MCP client. The catalogue lists this config verbatim from its source — it does not run, download, or vouch for the server. Review the command before you run it.

Transportstdio (runs a local command)
Env varsGEMINI_API_KEY PROJECT_ROOT RESPONSE_CHUNK_SIZE_KB CACHE_TTL_MS DEBUG GOOGLE_APPLICATION_CREDENTIALS GOOGLE_CLOUD_PROJECT VERTEX_AI_PROJECT
Claude Code 
claude mcp add --env GEMINI_API_KEY= --env PROJECT_ROOT= --env RESPONSE_CHUNK_SIZE_KB= --env CACHE_TTL_MS= --env DEBUG= --env GOOGLE_APPLICATION_CREDENTIALS= --env GOOGLE_CLOUD_PROJECT= --env VERTEX_AI_PROJECT= gemini-researcher -- npx gemini-researcher
Cursor

Add to Cursor

If the button doesn't open Cursor, use the JSON below — Cursor accepts the same mcpServers config.

VS Code 
code --add-mcp '{"name":"gemini-researcher","command":"npx","args":["gemini-researcher"],"env":{"GEMINI_API_KEY":"","PROJECT_ROOT":"","RESPONSE_CHUNK_SIZE_KB":"","CACHE_TTL_MS":"","DEBUG":"","GOOGLE_APPLICATION_CREDENTIALS":"","GOOGLE_CLOUD_PROJECT":"","VERTEX_AI_PROJECT":""}}'
JSON 
{
  "mcpServers": {
    "gemini-researcher": {
      "command": "npx",
      "args": [
        "gemini-researcher"
      ],
      "env": {
        "GEMINI_API_KEY": "",
        "PROJECT_ROOT": "",
        "RESPONSE_CHUNK_SIZE_KB": "",
        "CACHE_TTL_MS": "",
        "DEBUG": "",
        "GOOGLE_APPLICATION_CREDENTIALS": "",
        "GOOGLE_CLOUD_PROJECT": "",
        "VERTEX_AI_PROJECT": ""
      }
    }
  }
}

Environment variables are listed by name only — fill in your own values. Entries never carry secrets.