Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Gemini Interactions MCP ask what is quantum computing?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A FastMCP server for stateful Gemini conversations with automatic Google Search grounding.
Stateful Conversations: Maintain context across queries via interaction_id
Google Search Grounding: Model automatically searches the web when needed
URL Context: Parse and analyze linked web pages
Thinking Levels: Control reasoning depth (minimal, medium, high)
Related MCP server: Gemini Research MCP Server
uv sync
cp .env.example .env
# Edit .env with your GEMINI_API_KEYGet your API key from: https://aistudio.google.com/app/apikey
uv run python server.pyTool | Thinking Level | Description |
| minimal | Quick web search, structured results |
| medium | Balanced grounded answers |
| high | Deep reasoning with grounding |
All tools support interaction_id for stateful follow-up conversations.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"gemini": {
"command": "uv",
"args": ["run", "python", "/path/to/gemini-interactions-mcp/server.py"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
}MIT
This server cannot be deployed
MCP server for Google search results via SERP API
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
