---
title: MCP Server
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: docker
app_file: app.py
pinned: false
---

# MCP Server

This is a Multi-tool Chatbot Platform (MCP) server built with FastAPI, designed to be deployed on Hugging Face Spaces.

## Features

- **Calculator:** Perform basic arithmetic operations (sum, multiply, subtract, divide).
- **Email Drafter:** Draft emails based on your prompts using Google Gemini LLM.
- **PDF Q&A:** Upload a PDF and ask questions about its content, powered by Google Gemini LLM and Qdrant vector store.
- **Code Inspector:** Check Python code for syntax, logical errors, and best practices using Google Gemini LLM.

## How to use (Local)

1.  **Clone the repository:**
    ```bash
    git clone <repository_url>
    cd mcp-all
    ```
2.  **Create a virtual environment and activate it:**
    ```bash
    python -m venv venv
    ./venv/Scripts/activate  # On Windows
    source venv/bin/activate # On macOS/Linux
    ```
3.  **Install dependencies:**
    ```bash
    pip install -r requirements.txt
    ```
4.  **Set up Gemini API Key:**
    Obtain a Gemini API key from [Google AI Studio](https://aistudio.google.com/app/apikey).
    Set it as an environment variable named `GEMINI_API_KEY`.
    On Windows:
    ```bash
    set GEMINI_API_KEY=YOUR_API_KEY
    ```
    On macOS/Linux:
    ```bash
    export GEMINI_API_KEY=YOUR_API_KEY
    ```
5.  **Run the server:**
    ```bash
    python app.py
    ```
    The server will run on `http://0.0.0.0:7860`. Open your browser and go to `http://localhost:7860` to interact with the UI.

## How to use (Docker)

1.  **Build the Docker image:**
    ```bash
    docker build -t mcp-server .
    ```
2.  **Run the Docker container:**
    ```bash
    docker run -d -p 7860:7860 --env GEMINI_API_KEY=YOUR_API_KEY mcp-server
    ```
    Replace `YOUR_API_KEY` with your actual Gemini API key. The server will be accessible at `http://localhost:7860`.

## How to use (Hugging Face Spaces)

This project is configured for direct deployment on Hugging Face Spaces. Simply create a new Space, select "Docker" as the SDK, and link this repository. Ensure you add your `GEMINI_API_KEY` as a Space Secret in Hugging Face.

Once deployed, you can interact with the MCP server directly from your Hugging Face Space URL.

## Tool Usage Examples

- **Calculator:** "sum 10 and 5", "multiply 4 by 6", "subtract 20 from 8", "divide 100 by 10"
- **Email Drafter:** "draft an email to John about meeting next week regarding project X."
- **PDF Q&A:** Upload a PDF file and then type your question in the prompt.
- **Code Inspector:** "check code: print('Hello')\n  print('World')"