Pollinations

A Model Context Protocol (MCP) server that enables AI assistants to generate images, text, and audio through the Pollinations APIs. Supports customizable parameters, image saving, and multiple model options.
  • javascript

39

GitHub Stars

javascript

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": {
    "pinkpixel-dev-mcpollinations": {
      "command": "npx",
      "args": [
        "-y",
        "@pinkpixel/mcpollinations"
      ],
      "env": {
        "token": "YOUR_TOKEN_OPTIONAL",
        "referrer": "your-app-or-domain-optional",
        "IMAGE_SAFE": "false",
        "OUTPUT_DIR": "./mcpollinations-output",
        "TEXT_MODEL": "openai",
        "TEXT_TOP_P": "0.9",
        "AUDIO_VOICE": "alloy",
        "IMAGE_MODEL": "flux",
        "IMAGE_WIDTH": "1024",
        "IMAGE_HEIGHT": "1024",
        "IMAGE_ENHANCE": "true",
        "TEXT_TEMPERATURE": "0.7",
        "POLLINATIONS_TOKEN": "YOUR_API_TOKEN",
        "POLLINATIONS_REFERRER": "https://your-domain.com"
      }
    }
  }
}

You can run and configure the MCPollinations server to generate images, text, and audio from prompts, then use those outputs with any MCP-enabled assistant. It is lightweight, requires no authentication by default, and supports a range of image, text, and audio generation options through the Pollinations APIs.

How to use

Use an MCP client to send prompts to the MCPollinations server. When you request content, your configured defaults (models, output directory, and generation parameters) are used automatically. You can override specific settings for a single request by explicitly instructing the assistant, for example to change the image model or save location.

How to install

Prerequisites: Node.js 14.0.0 or higher (Node.js 16.x or higher is recommended for best performance). Ensure your environment can run npm or npx.

# Run directly with npx (no installation required)
npx @pinkpixel/mcpollinations

# Install globally
npm install -g @pinkpixel/mcpollinations

# Run the server
mcpollinations
# or
npx @pinkpixel/mcpollinations

Configuration and authentication

You can enable optional authentication to access more models and higher rate limits. The server works perfectly without authentication, but tokens provide enhanced access.

{
  "mcpollinations": {
    "command": "npx",
    "args": ["-y", "@pinkpixel/mcpollinations"],
    "env": {
      "token": "YOUR_TOKEN_OPTIONAL",
      "referrer": "your-app-or-domain-optional",
      "IMAGE_MODEL": "flux",
      "IMAGE_WIDTH": "1024",
      "IMAGE_HEIGHT": "1024",
      "IMAGE_ENHANCE": "true",
      "IMAGE_SAFE": "false",
      "TEXT_MODEL": "openai",
      "TEXT_TEMPERATURE": "0.7",
      "TEXT_TOP_P": "0.9",
      "TEXT_SYSTEM": "",
      "AUDIO_VOICE": "alloy",
      "OUTPUT_DIR": "./mcpollinations-output"
    }
  }
}

Using your configuration settings

MCPollinations respects your configured defaults in env when you generate content. To override, tell the assistant what to change, for example to use a different image model or save results to a specific folder.

Troubleshooting

If you see an AbortController error on startup, it is usually due to an older Node.js version. Upgrade to Node.js 16.0.0 or newer. If upgrading isn’t possible, install the AbortController polyfill or use a global installation of the package.

node --version

If the version is below 16.0.0, consider upgrading. You can also upgrade the package globally and run with npx:

npm install -g @pinkpixel/mcpollinations
npx @pinkpixel/mcpollinations

Notes on image and file handling

Images and outputs are generated according to your configured paths and models. If you specify custom save paths, use absolute paths on Windows for reliability.

Available tools

generateImageUrl

Generates an image URL from a text prompt using the configured image model.

generateImage

Generates an image from a text prompt, returns base64 data, and saves to disk by default (PNG).

editImage

Edit or modify an existing image based on a text prompt.

generateImageFromReference

Create new images from an existing image reference using a selected image model.

listImageModels

List available image generation models.

respondText

Generate a text response from a prompt using a text model with configurable temperature, top_p, and system prompts.

respondAudio

Generate an audio response from a text prompt with a selectable voice.

listTextModels

List available text generation models.

listAudioVoices

List all available voices for audio generation.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational