drkhan107/mcp_gemini
If you are the rightful owner of mcp_gemini and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A working demo of MCP integrated with Google's Gemini.
The Model Context Protocol (MCP) server is a robust framework designed to facilitate seamless integration and communication between various machine learning models and applications. By leveraging the capabilities of Google's Gemini, this MCP server provides a comprehensive environment for deploying, managing, and interacting with machine learning models. The server is built to handle real-time data streams and offers a user-friendly interface for both developers and end-users. With its modular architecture, the MCP server can be easily extended to support additional functionalities and integrations, making it a versatile tool for a wide range of applications.
Features
- Real-time data streaming: Supports real-time data processing and communication between models and applications.
- Integration with Google's Gemini: Leverages the power of Google's Gemini for enhanced model performance and capabilities.
- User-friendly interface: Provides an intuitive interface for easy interaction and management of models.
- Modular architecture: Allows for easy extension and integration of additional functionalities.
- Cross-platform compatibility: Can be deployed and used across various platforms and environments.
Usages
usage with local integration stdio
python mcp.run(transport='stdio') # Tools defined via @mcp.tool() decorator
usage with local integration subprocess
python command='uv', args=['run', 'server.py'] # Launch using virtual environment
usage with remote integration sse
python mcp.run(transport='sse', host="0.0.0.0", port=8000) # Specify SSE endpoint
usage with remote integration streamable http
yaml
paths:
/mcp:
post:
x-ms-agentic-protocol: mcp-streamable-1.0 # Copilot Studio integrationusage with platform integration github
{"command": "docker", "args": ["run", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"]}usage with platform integration fastmcp
python
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...
