The Google Researcher MCP Server provides tools for AI assistants to perform web searches, scrape content from various document types, and extract information from academic papers and patents.
From the registry: MCP server providing Google Search, web scraping, and multi-source research tools for AI assistants
Please install the `google-researcher` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Node.js runtime version 20 or newer
- **Google Custom Search credentials** — Create a Google Custom Search API key and Custom Search Engine ID (https://programmablesearchengine.google.com/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","google-researcher-mcp"]
- required environment variables:
- `GOOGLE_CUSTOM_SEARCH_API_KEY`: Google Custom Search API key (example: `<your-api-key>`)
- `GOOGLE_CUSTOM_SEARCH_ID`: Google Programmable Search Engine ID (example: `<your-search-engine-id>`)
Note: Chromium is auto-installed on first run via Playwright. Also supports HTTP+SSE transport with OAuth 2.1.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GOOGLE_CUSTOM_SEARCH_API_KEYrequiredAPI key for Google Custom SearchGOOGLE_CUSTOM_SEARCH_IDrequiredSearch ID for Google Custom SearchMCP server for searching Airweave collections with natural language queries.