Model Context Protocol

Provides an MCP Server to interact with a file system via HTTP with Gemini-based summarization.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "vijayk-213-model-context-protocol": {
      "command": "uvicorn",
      "args": [
        "mcp_server:app",
        "--host",
        "127.0.0.1",
        "--port",
        "8000",
        "--reload"
      ],
      "env": {
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY",
        "MCP_SERVER_URL": "http://127.0.0.1:8000"
      }
    }
  }
}

You can run an MCP Server that exposes file system operations over HTTP and integrates with the Google Gemini API to summarize file contents. This server lets you read, create, copy, move, and delete files, streaming large files as needed, all through a simple MCP interface. It is built with Python, FastAPI, and the MCP framework, and can be deployed locally or to Cloud Run for scalable access.

How to use

To work with the MCP Server, start by running the local server and then interact with it through an MCP client. The server provides endpoints to read text from files and to invoke MCP functions. You can leverage Gemini-based summarization for content processing as part of your workflows.

How to install

Prerequisites: you need Python 3.9 or newer installed on your machine.

Clone the project to your workspace.
Create and activate a virtual environment.
Install dependencies from the requirements file.
Set environment variables for the MCP server and Google Gemini integration.
Start the MCP server using the recommended runtime command.

Configuration and startup details

Environment variables you need to configure include the MCP server URL and the Gemini API key. The server will be accessible at the host and port you specify when starting the MCP server.

Example MCP server configuration

{
  "mcpServers": {
    "filefs": {
      "type": "stdio",
      "name": "filefs_mcp",
      "command": "uvicorn",
      "args": ["mcp_server:app", "--host", "127.0.0.1", "--port", "8000", "--reload"],
      "env": [
        {"name": "MCP_SERVER_URL", "value": "http://127.0.0.1:8000"},
        {"name": "GEMINI_API_KEY", "value": "YOUR_GEMINI_API_KEY"}
      ]
    }
  }
}

Usage notes

The server supports reading common text-based formats and streaming large files. Use the provided MCP endpoints to read text from files and to invoke functions that leverage Gemini-based summarization for content processing. When you deploy to Cloud Run, ensure the service is exposed with a stable URL and that environment credentials for Gemini are securely provided.

Troubleshooting and tips

If you encounter connection issues, verify that the MCP server is running on the expected host and port, and that the Gemini API key is set correctly. Check that the environment variables are propagated to the running process and that the server has network access to the Gemini API.

Available tools

readTextFromFile

Reads the contents of a text file from the specified path and returns the text content, supporting multiple encodings and streaming for large files.

invokeMcpFunction

Calls an MCP function exposed by the server to perform a specific operation on a file or dataset, enabling chained processing workflows.

Built by

VeilStrat

AI signals for GTM teams