mcp-gemini-grounded-search
Verified Safeby cnosuke
Overview
Provides grounded search functionality using Google's Gemini API, allowing MCP clients to perform web searches and retrieve up-to-date information with sources.
Installation
docker run -i --rm -e GEMINI_API_KEY="your-api-key" cnosuke/mcp-gemini-grounded-search:latestEnvironment Variables
- LOG_PATH
- DEBUG
- GEMINI_API_KEY
- GEMINI_MODEL_NAME
- GEMINI_MAX_TOKENS
- GEMINI_QUERY_TEMPLATE
Security Notes
The server correctly handles the Gemini API key, requiring it via environment variables, config file, or command line arguments, preventing hardcoding. Communication occurs via standard I/O (ServeStdio), minimizing direct network attack surface. Uses standard, well-vetted Go libraries. No 'eval' or similar dangerous patterns are present. Logging is configurable, allowing sensitive data control.
Similar Servers
mcp-devtools
A high-performance MCP server providing a unified, modular interface to essential developer tools for AI agents, replacing multiple Node.js/Python-based solutions with an efficient Go binary.
GeminiMCP
MCP server integrating with Google's Gemini API for code analysis, general queries, and search with grounding capabilities.
gemini-mcp
Serves as a Model Context Protocol (MCP) gateway to Google Gemini AI services, enabling multimodal generation including image creation, editing, and video production.
search-context
Provides semantic search over documentation using Google's Gemini File Search API, returning AI-generated answers with source citations.