README.md

---
license: apache-2.0
title: Text Processing MCP Server
sdk: gradio
emoji: 📚
colorFrom: green
colorTo: green
short_description: Text Processo
---
# Text Processing MCP Server

A Gradio-based MCP (Model Context Protocol) server that provides various text processing tools.

## Features

This server provides the following text processing tools:

- **Letter Counter**: Count occurrences of a specific letter in text
- **Text Length Calculator**: Calculate the number of characters in text
- **Text Reverser**: Reverse the input text
- **Word Counter**: Count the number of words in text
- **Text to Uppercase**: Convert text to uppercase
- **Text to Lowercase**: Convert text to lowercase

## Usage

### Web Interface
Visit the Gradio interface to use the tools directly in your browser.

### MCP Integration
This server can be connected to MCP clients. The MCP endpoint is available at:
- **Streamable HTTP URL**: `https://your-space-name.hf.space/gradio_api/mcp/`
- **SSE URL (deprecated)**: `https://your-space-name.hf.space/gradio_api/mcp/sse`

### Connecting to MCP Clients

#### Cursor IDE
Add this configuration to your Cursor MCP settings:

```json
{
  "mcpServers": {
    "text-processing": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://your-space-name.hf.space/gradio_api/mcp/",
        "--transport",
        "sse-only"
      ]
    }
  }
}
```

#### Claude Desktop
Similar configuration can be used for Claude Desktop application.

## Local Development

To run locally:

1. Install dependencies:
   ```bash
   pip install gradio[mcp]
   ```

2. Run the server:
   ```bash
   python app.py
   ```

3. Access the interface at `http://localhost:7860`
4. MCP endpoint will be available at `http://localhost:7860/gradio_api/mcp/`

## MCP Tools Available

The server exposes the following MCP tools:
- `letter_counter(word: str, letter: str) -> int`
- `word_length_calculator(text: str) -> int`
- `text_reverser(text: str) -> str`
- `word_counter(text: str) -> int`
- `text_to_uppercase(text: str) -> str`
- `text_to_lowercase(text: str) -> str`

Each tool includes proper type hints and documentation for seamless MCP integration.