How do I get an API key for Pollinations?
Sign up at enter.pollinations.ai to generate a publishable key (`pk_`) for client-side use or a secret key (`sk_`) for server-side use. Secret keys should never be exposed in client-side code.
Pollinations MCP Server
@pollinations
基本信息
关于 Pollinations MCP Server
Your Friendly Open-Source Gen-AI Platform
Pollinations MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"pollinations": {
"command": "npx",
"args": [
"@pollinations/mcp"
]
}
}
}Pollinations MCP Server 工具
23Generate an image URL from a text prompt. Returns a shareable/embeddable URL without downloading the image. Supports all image models and parameters including image-to-image with the 'image' parameter.
Generate an image from a text prompt and return the base64-encoded image data. Full control over all generation parameters. Supports image-to-image with kontext, seedream, nanobanana models.
Generate multiple images in parallel (up to 10). Best with sk_ keys (no rate limits). pk_ keys will be rate-limited. Each prompt generates one image with shared parameters.
Generate a video from a text prompt or image. Models: veo (text-to-video, 4-8s, audio), seedance (text/image-to-video, 2-10s), seedance-pro (best quality). Use 'image' parameter with seedance models for image-to-video generation.
Generate a video URL from a text prompt. Returns a shareable/embeddable URL without downloading the video. Models: veo (4-8s, audio), seedance (2-10s), seedance-pro (best quality).
Analyze and describe an image using vision-capable AI models. Pass an image URL and optionally a custom prompt. Great for image captioning, content analysis, OCR, and visual Q&A.
Analyze a video using AI. Supports YouTube URLs and direct video links. Uses gemini-large for native video understanding (frames + audio). Great for video summarization, content analysis, and Q&A about videos.
List all available image and video generation models with their capabilities. Shows which models support image-to-image, video generation, and other features. Models are fetched dynamically from the API.
Generate text from a simple prompt. Easy-to-use text generation with essential parameters. For advanced features (tool calling, multi-turn, audio), use chatCompletion instead.
OpenAI-compatible chat completions with ALL parameters. Supports: - Multi-turn conversations with message history - Function/tool calling for AI agents - Audio input/output (openai-audio model) - Reasoning mode (kimi, perplexity-reasoning, openai-large, gemini-large) - JSON/structured output - Built-in Gemini tools (google_search, code_execution, etc.) - Perplexity web search with citations
List all available text generation models with their capabilities. Shows which models support reasoning, tools, audio, vision, etc. Models are fetched dynamically from the API.
Search the web for real-time information using search-enabled models. Returns answers with source citations. Great for current events, facts, research.
Get pricing information for all models. Shows cost per token/image in pollen.
Generate an audio response to a text prompt. The AI will respond to your prompt with speech.
Generate speech that says the provided text verbatim. Direct text-to-speech.
List all available audio voices and supported formats. Voices are fetched dynamically from the API.
Transcribe audio from a URL. Uses gemini-large for accurate speech-to-text transcription.
Set your pollinations.ai API key for authenticated requests. Get your key at https://enter.pollinations.ai/keys
Get information about the currently set API key
Clear the stored API key
Get the current Pollen balance for the authenticated API key. Returns key-scoped balance if the key has its own budget, otherwise account-wide. Requires an API key with 'account:usage' permission.
Get usage history for the authenticated key. By default returns the most recent per-request records (model, cost, tokens, latency). Set 'daily: true' for a daily aggregated summary grouped by date and model. Requires 'account:usage' permission.
List quests and earned rewards for the authenticated account. Read-only; claiming rewards requires a dashboard session. Requires 'account:usage' permission.
概览
What is Pollinations?
Pollinations is an open-source generative AI platform that provides APIs for text, image, video, and audio generation. It powers over 500 community projects and includes an MCP (Model Context Protocol) server so AI assistants like Claude can generate images and audio directly.
How to use Pollinations?
You can use Pollinations via its web interface at pollinations.ai, by calling the unified API at gen.pollinations.ai, or by running the MCP server with npx @pollinations/mcp and adding the corresponding configuration to your MCP client. API keys (publishable pk_ or secret sk_) are obtained at enter.pollinations.ai.
Key features of Pollinations
- 100% open-source code, decisions, and roadmap
- Unified API endpoint for text, image, audio, and video generation
- Pollen credits pay-as-you-go system ($1 ≈ 1 Pollen)
- Multiple models: Flux, GPT, Claude, Gemini, Seedream, and more
- MCP server for AI assistants to generate images and audio
- CLI tool:
npx @pollinations/cli
Use cases of Pollinations
- Generate images from text descriptions for creative projects
- Integrate text-to-speech audio into applications with multiple voices
- Build AI-powered apps using the unified API and Pollen credits
- Enable AI assistants to generate media directly via the MCP server
- Run community-built models through the decentralized registry
常见问题
What models are available on Pollinations?
Pollinations supports image generation (Flux, GPT Image, Seedream, Kontext), video generation (Seedance, Veo in alpha), audio (text-to-speech and speech-to-text), and text generation via models like GPT, Claude, and Gemini. The unified API gives access to all models in one place.
How do I use the MCP server for Pollinations?
Add the configuration `{"mcpServers":{"pollinations":{"command":"npx","args":["@pollinations/mcp"]}}}` to your MCP client, or run `npx @pollinations/mcp` directly. The server lets AI assistants generate images, create text-to-speech audio, and list available models.
What are Pollen credits?
Pollen credits are a simple pay-as-you-go system where $1 equals approximately 1 Pollen. Credits are consumed per API request; publishable keys have a rate limit of 1 Pollen per IP per hour (beta), while secret keys have no rate limits.
Can I restrict which models an API key can access?
Yes. When creating a key at enter.pollinations.ai, you can choose to allow all models or restrict it to specific models such as `flux` or `gptimage-large`.
其他 分类下的更多 MCP 服务器
YOUB
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
26.0K
Lemon.io
lemon-ioRequest dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
Codelf
unbugA search tool helps dev to solve the naming things problem.
14.2K
DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
评论