MCP 服务器

Nectar-MCP

Nectar is a stdio MCP server for Pollinations image and video generation. It gives MCP clients a small, focused toolset for generating images, editing images, generating videos, listing available image/video models, and checking pollen balance.

README

Nectar MCP

It is intentionally not a full Pollinations wrapper. No text generation, no audio, no embeddings, no sprawling control panel. Just the creative media tools this server actually needs.

Tools

Tool	Purpose
`pollinations_list_models`	Lists current image and video models from Pollinations using a 15-minute cache, compact summaries by default, sorting, and capability filters.
`pollinations_get_model_details`	Returns full metadata for one model by name or alias.
`pollinations_generate_image`	Generates an image from a text prompt with model, size/dimensions, quality, seed, safety, transparency, prompt enhancement, negative prompt, reference image, and response format options.
`pollinations_edit_image`	Edits one or more image URLs using a text prompt, with model, size/dimensions, quality, seed, safety, transparency, prompt enhancement, negative prompt, and response format options.
`pollinations_generate_video`	Generates a video from a text prompt, with model, duration, aspect ratio, resolution, seed, audio, safety, quality, and reference-frame controls.
`pollinations_check_balance`	Checks the authenticated pollen balance or API key budget.

Requirements

Node.js 20 or newer
A Pollinations API key from enter.pollinations.ai

Model listing does not require authentication. Generation and balance tools require POLLINATIONS_API_KEY.

Generated images, edited images, and videos are saved locally by default. Set NECTAR_OUTPUT_DIR in your MCP client env block to choose the default output folder, or pass output_dir per tool call.

Install

MCP Client Config

Most MCP clients should pass the API key through the server env block:

{
  "mcpServers": {
    "pixara": {
      "command": "npx",
      "args": ["-y", "@pinkpixel/nectar-mcp"],
      "env": {
        "POLLINATIONS_API_KEY": "sk_your_key_here",
        "NECTAR_OUTPUT_DIR": "/absolute/path/to/nectar-output"
      }
    }
  }
}

For local development:

git clone https://github.com/pinkpixel-dev/nectar-mcp.git
cd nectar-mcp
npm install
npm run build

{
  "mcpServers": {
    "nectar": {
      "command": "node",
      "args": ["/absolute/path/to/nectar-mcp/dist/index.js"],
      "env": {
        "POLLINATIONS_API_KEY": "sk_your_key_here",
        "NECTAR_OUTPUT_DIR": "/absolute/path/to/nectar-output"
      }
    }
  }
}

Example Requests

Ask your MCP client:

List Pollinations video models and help me choose one for a 9:16 product teaser.

Generate a 1024x1024 image of a tiny yellow robot painter in a polished dark UI style.

Edit this image URL so the background is transparent and the subject looks more premium.

Generate a 6 second 16:9 video of a glowing pollen trail drifting across a dark studio surface.

Notes

Image generation uses Pollinations' OpenAI-compatible image generation endpoint.
Image editing currently supports image URLs. Local multipart file upload is intentionally left out of v1.
Image/video tools default to save_output: true, converting base64 responses and downloaded URLs into local files.
Image generation and image editing default to Pollinations response_format: "b64_json" because local decoding is the most reliable save path.
Saved files go to output_dir, NECTAR_OUTPUT_DIR, or ./nectar-output, in that order.
Saved Pollinations media URLs are downloaded with the configured POLLINATIONS_API_KEY. Nectar does not send that key to non-Pollinations URLs.
Tool descriptions intentionally include model examples, parameter guidance, return shape notes, and error-handling hints so MCP clients have enough context to call the tools correctly.
Model listing is compact by default. Use pollinations_get_model_details when an agent needs full raw metadata for one model.
Video generation returns the final media URL and response metadata.
Model support varies by capability, so call pollinations_list_models before using model-specific options.
The server never stores your API key. Your MCP client passes it through the process environment.