pollo-mcp/README.md

Pollo AI Model Context Protocol (MCP) Server for video generation

# Pollo MCP Server

Official Pollo Model Context Protocol (MCP) server that enables interaction with powerful Text to video generation APIs.

## Features

- Generate video from image or text prompt
- Get generation task status
- Automatically download the generated video

**Note**: Before using the service, you need to have the pollo.ai [API key](https://pollo.ai/api-platform/keys).

## Installation

```bash
npm install -g pollo-mcp
```

## Quick Start

Pollo MCP Server implements the [Model Context Protocol (MCP)](https://github.com/anthropics/model-context-protocol) specification and can be used as a server to interact with MCP-compatible clients (such as Cursor).

### Quickstart with Cursor

1. Get your API key from [Pollo.ai](https://pollo.ai/api-platform/keys).
2. Make sure that you already installed [Node.js and npm](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm)

Go to `Cursor → Preferences → Cursor Settings → MCP Tools → New MCP Server`, add config

```json
{
  "mcpServers": {
    "pollo.ai": {
      "command": "npx",
      "args": ["-y", "mcp-server-pollo"],
      "env": {
        "POLLO_AI_BASE_URL": "https://pollo.ai",
        "POLLO_AI_API_KEY": "<your-api-key>",
        "POLLO_AI_HOME_DIR": "<path to save generated videos>",
        "POLLO_AI_VIDEO_MODEL_IMG": "<Model for generating videos from images, optional, pollo-v1-6 is used by default, multiple models are separated by commas>",
        "POLLO_AI_VIDEO_MODEL_TEXT": "<Model for generating videos from text, optional, pollo-v1-6 is used by default, multiple models are separated by commas>"
      }
    }
  }
}
```

### Quickstart with Claude Desktop

Go to `Claude > Settings > Developer > Edit Config > claude_desktop_config.json` to add above config.

That's it. Your MCP client can now interact with Pollo.ai through these tools.

### Tools

- **text2video**

  - Generate video from text prompt.
  - Input: supports multiple models, for a detailed list, see [Pollo AI API Platform](https://docs.pollo.ai/)

- **img2video**

  - Generate video from image.
  - Input: supports multiple models, for a detailed list, see [Pollo AI API Platform](https://docs.pollo.ai/)

- **getTaskStatus**

  - Check generation task status, and automatically download the completed video.
  - Inputs:
    - `taskId` (string): generation task id returned by **text2video** and **img2video**