MCPollinations Multimodal MCP Server
@pinkpixel-dev
About MCPollinations Multimodal MCP Server
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.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcpollinations": {
"command": "npx",
"args": [
"-y",
"@pinkpixel/mcpollinations"
],
"resources": {
"output_dir": "./mcpollinations-output"
},
"default_params": {
"image": {
"model": "flux",
"width": 1024,
"height": 1024,
"safe": false,
"enhance": true
},
"text": {
"model": "openai"
},
"audio": {
"voice": "alloy"
}
}
}
}
}Tools
9Generate an image URL from a text prompt. User-configured settings in MCP config will be used as defaults unless specifically overridden.
Generate an image, return the base64-encoded data, and save to a file by default. User-configured settings in MCP config will be used as defaults unless specifically overridden.
Edit or modify an existing image based on a text prompt. User-configured settings in MCP config will be used as defaults unless specifically overridden.
Generate a new image using an existing image as reference. User-configured settings in MCP config will be used as defaults unless specifically overridden.
List available image models
Generate an audio response to a text prompt and play it through the system
List all available audio voices for text-to-speech generation
Respond with text to a prompt using the Pollinations Text API. User-configured settings in MCP config will be used as defaults unless specifically overridden.
List available text models
Overview
What is MCPollinations Multimodal MCP Server?
MCPollinations Multimodal MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to generate images, text, and audio through the Pollinations APIs. It requires no authentication for the free tier and is designed for developers integrating generative AI into MCP-compatible applications.
How to use MCPollinations Multimodal MCP Server?
Run directly with npx @pinkpixel/mcpollinations, install globally with npm install -g @pinkpixel/mcpollinations, or clone from GitHub. Generate an MCP configuration file with npx @pinkpixel/mcpollinations generate-config, then copy the generated mcp.json into your MCP client’s settings and restart. Optional authentication can be set via environment variables or the env block in the MCP config.
Key features of MCPollinations Multimodal MCP Server
- Generate image URLs or base64-encoded images saved as PNG/JPEG/WEBP
- Generate text responses with configurable model, temperature, and top_p
- Generate audio responses from text prompts
- Edit existing images or create variations from reference images
- List available image models, text models, and audio voices
- Optional authentication for enhanced access and rate limits
Use cases of MCPollinations Multimodal MCP Server
- Generate an image from a text prompt using the
generateImageorgenerateImageUrltool - Edit or modify an existing image by providing a URL and a text instruction (e.g., “change background to sunset”)
- Produce a text response from an AI model with custom system instructions and temperature
- Create audio narration or voice responses from text prompts using
respondAudio - List available models or voices to choose the best fit for a generation task
FAQ from MCPollinations Multimodal MCP Server
Is authentication required?
No, the server works without authentication on the free tier. You can optionally provide a Pollinations API token and referrer URL for enhanced access and better rate limits.
What are the system requirements?
Node.js version 14.0.0 or higher is required, with Node.js 16.0.0 or newer recommended for best performance and to avoid the need for an AbortController polyfill.
Which models are available for image generation?
Available models include flux (default), turbo, kontext, nanobanana, and seedream. Use listImageModels to see the current list.
Can I edit images locally?
The editImage and generateImageFromReference tools require publicly accessible HTTP(S) URLs. Local file paths or base64 data URLs are not supported; you must host the image online and provide the URL.
What is the default image output format?
When using generateImage, images are saved as PNG files by default, and base64-encoded image data is always returned regardless of file saving.
Frequently asked questions
Is authentication required?
No, the server works without authentication on the free tier. You can optionally provide a Pollinations API token and referrer URL for enhanced access and better rate limits.
What are the system requirements?
Node.js version 14.0.0 or higher is required, with Node.js 16.0.0 or newer recommended for best performance and to avoid the need for an AbortController polyfill.
Which models are available for image generation?
Available models include `flux` (default), `turbo`, `kontext`, `nanobanana`, and `seedream`. Use `listImageModels` to see the current list.
Can I edit images locally?
The `editImage` and `generateImageFromReference` tools require publicly accessible HTTP(S) URLs. Local file paths or base64 data URLs are not supported; you must host the image online and provide the URL.
What is the default image output format?
When using `generateImage`, images are saved as PNG files by default, and base64-encoded image data is always returned regardless of file saving.
Basic information
More Media & Design MCP servers
百度地图 MCP Server
baidu-mapsBaidu Map MCP Server
Uwear.ai
Uwear.aiRun complete AI fashion photoshoots from ChatGPT, Claude, or Codex. Turn flat-lay, packshot, and mannequin product images into catalog-ready on-model photos and video with saved art direction, automatic QA, and catalog-s
Lamina — On-brand product photos, video & try-ons
LaminaGenerate on brand product videos from Claude Code (or any assistant) in one line. Lamina turns a brief + your brand kit into finished product photos, video reels, and campaign banners - no prompt engineering; brand guard
Katto
KattoAI video clipping MCP server: turn long videos, podcasts and Twitch VODs into scored, captioned 9:16 shorts from Claude, Cursor, ChatGPT and any MCP client.
AI Manga & Anime Generator - Mangii MCP
AAAIStudioPublic Mangii MCP metadata (ai.mangii/manga). Remote Streamable HTTP at mcp.mangii.ai.
Comments