MCP Gemini Grounded Search

A Go-based MCP server providing grounded search functionality using Google's Gemini API.

MCP Gemini Grounded Search is a Go-based MCP server that provides grounded search functionality using Google's Gemini API. MCP clients such as Claude Desktop and Claude Code can perform real-time web searches and retrieve up-to-date information with source attribution.

- MCP Compliance: JSON-RPC based interface for tool execution per the MCP specification
- Grounded Search: Gemini API generates answers with source attributions
- Two Transport Modes: stdio (for Claude Desktop / Claude Code) and Streamable HTTP
- Flexible Configuration: config file, environment variables, or command-line flags

docker pull cnosuke/mcp-gemini-grounded-search:latest docker run -i --rm -e GEMINI_API_KEY="your-api-key" cnosuke/mcp-gemini-grounded-search:latest server

Add an entry to yourclaude_desktop_config.json:

{ "mcpServers": { "gemini-search": { "command": "docker", "args": ["run", "-i", "--rm", "-e", "GEMINI_API_KEY=your-api-key", "cnosuke/mcp-gemini-grounded-search:latest", "server"] } } }

claude mcp add-json mcp-gemini-grounded-search '{ "command": "docker", "args": [ "run", "-i", "--rm", "-e", "GEMINI_API_KEY", "-e", "GEMINI_MODEL_NAME", "-e", "GEMINI_THINKING_LEVEL", "cnosuke/mcp-gemini-grounded-search:latest", "server" ], "env": { "GEMINI_MODEL_NAME": "gemini-3.6-flash", "GEMINI_THINKING_LEVEL": "LOW", "GEMINI_API_KEY": "<your-gemini-api-key>" } }'

# Build make bin/mcp-gemini-grounded-search # stdio mode (for Claude Desktop / Claude Code) ./bin/mcp-gemini-grounded-search server --config config.yml # Streamable HTTP mode ./bin/mcp-gemini-grounded-search httpserver --config config.yml

{ "mcpServers": { "gemini-search": { "command": "/path/to/mcp-gemini-grounded-search", "args": ["server", "--config", "/path/to/config.yml"], "env": { "GEMINI_API_KEY": "your-api-key" } } } }

Thehttpserversubcommand starts an HTTP server compatible with the MCP Streamable HTTP transport.

HTTP_AUTH_TOKEN=secret GEMINI_API_KEY=your-key \ ./bin/mcp-gemini-grounded-search httpserver --config config.yml # Health check (no auth required) curl http://localhost:8080/health # MCP endpoint (auth required) curl -H "Authorization: Bearer secret" http://localhost:8080/mcp

HTTP-specific settings can be configured entirely via environment variables — no need to put secrets in config.yml.

log: 'path/to/mcp-gemini-grounded-search.log' # empty = no log output debug: false gemini: api_key: '' # Set via GEMINI_API_KEY env var model_name: 'gemini-3.6-flash' max_tokens: 5000 thinking_level: 'LOW' # Gemini 3.x series: MINIMAL, LOW, MEDIUM, HIGH # thinking_budget: 0 # Gemini 2.5 series: token count (0 = disable thinking) http: port: 8080 endpoint_path: /mcp auth_token: '' # Set via HTTP_AUTH_TOKEN env var allowed_origins: [] # e.g. ['https://example.com'] — empty = allow all heartbeat_seconds: 30

Configuration priority:defaults → config.yml → environment variables

./bin/mcp-gemini-grounded-search server [options]

./bin/mcp-gemini-grounded-search httpserver [options]

All HTTP settings (port,auth_token, etc.) are configured via environment variables or config.yml.

Performs a web search using the Gemini API and returns a grounded answer with sources.

{ "text": "Generated answer text", "groundings": [ { "title": "Source title", "domain": "example.com", "url": "https://example.com/article" } ] }

- Setlogin config.yml orLOG_PATHenv var to write logs to a file
- Iflogis empty, no log file is produced
- Setdebug: trueorDEBUG=truefor verbose logging

Contributions are welcome. Please fork the repository and submit pull requests for improvements or bug fixes. For major changes, open an issue first to discuss your ideas.

This project is licensed under the MIT License.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

A connector for the Perplexity API to enable web search within the MCP ecosystem.

Structural AI Search Readiness MCP. Audit, dry-run fixes, rescore, doctor. No LLM rankings.

Perform web searches with the Brave Search API and analyze research papers using Google's Gemini model.

Provides AI-powered web search and summarization using the Gemini API's grounding feature.

Integrate search grounded Gemini output into your workflow.

Generates responses using the Gemini API and Google Search for up-to-date information.

Performs web searches using the Gemini Web Search Tool via the local gemini-cli.

A server providing Google AI-powered search and documentation tools for developers.

Comprehensive web, news, and social media search and analysis using xAI's Grok API.

Enhances LLM responses with factual, real-time web content using Jina AI's grounding capabilities.