# doctorm333/promptpilot-mcp-server [Health: Active]

**Category:** 🎨 Art & Culture  
**Repository:** https://github.com/doctorm333/promptpilot-mcp-server  
**GitHub Stars:** 2  
**npm Downloads (last month):** 107  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/doctorm333-promptpilot-mcp-server

## Description
Generate images, video, and audio via 20+ AI models (Flux, GPT-Image-1, Imagen 4, Grok, Seedance, ElevenLabs). Prompt builder with styles, lighting, camera, mood presets. Batch generation support.

## Tools
Capabilities this server exposes over MCP:

- **list_models** — List all available models for image, video, and audio generation with their type and pricing
- **list_styles** — List all available styles, lighting, camera angles, moods, colors, and quality tags for prompt building
- **build_prompt** — Build an optimized prompt from subject + style/lighting/camera/mood/color/quality options
- **generate_image** — Generate an image using Pollinations API. Returns a URL to the generated image.
- **generate_video** — Generate a video using Pollinations API. Returns a URL to the generated video.
- **generate_audio** — Generate audio (speech or music) using Pollinations API. Returns a URL to the generated audio.
- **check_balance** — Check your Pollinations API balance (pollen). Shows remaining credits for paid models.
- **generate_batch** — Generate multiple images in one call (up to 10). More efficient than calling generate_image repeatedly.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "promptpilot-mcp-server": {
    "command": "npx",
    "args": ["-y","promptpilot-mcp"],
    "env": {
      "POLLINATIONS_API_KEY": ""
    }
  }
}
```

**Requires environment variables:** `POLLINATIONS_API_KEY` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What doctorm333/promptpilot-mcp-server does

doctorm333/promptpilot-mcp-server exposes Pollinations media-generation features through MCP. An agent can request images, video, speech, or music and receive a URL for the generated result. The server also provides discovery and prompt-composition tools, so an agent can inspect available models and build prompts from structured creative options.

The available model catalog covers image, video, and audio generation. The README identifies examples including Flux, GPT-Image-1, Imagen 4, Grok Imagine, Seedance, and ElevenLabs text-to-speech. Availability and pricing are exposed through the model-listing tool rather than hardcoded assumptions in the agent workflow.

## How it works

The server runs as an MCP process and communicates with an MCP client over standard input and output. Requests are forwarded to the Pollinations API for generation. Image, video, and audio tools return URLs instead of embedding the generated media in the tool response.

Prompt construction is separate from generation. An agent can first inspect style, lighting, camera, mood, color, and quality presets, then pass selected values to the prompt builder. It can use the resulting prompt with a generation tool. Batch generation supports up to 10 images in one call, which is useful for producing multiple image results without issuing separate image requests.

The check-balance tool reports remaining Pollinations credits, called pollen, for paid models. Free models do not require a Pollinations key; paid models do.

## Setup and configuration

To install doctorm333/promptpilot-mcp-server, configure the package as an MCP stdio server with `npx -y promptpilot-mcp`. The README provides configurations for Claude Code, Claude Desktop, Cursor, Windsurf, and VS Code. It also documents a Docker invocation using the `mcp/promptpilot-mcp` image.

Set `POLLINATIONS_API_KEY` in the MCP server environment when the agent needs paid models. The key is not required for free models. The same environment variable can be passed to the Docker container with `-e`.

## Tools and capabilities

The eight documented tools are:

- `list_models`: shows image, video, and audio models with type and pricing information.
- `list_styles`: returns style, lighting, camera, mood, color, and quality options.
- `build_prompt`: creates a prompt from a subject and selected preset values.
- `generate_image`: requests an image and returns its URL.
- `generate_video`: requests a video and returns its URL.
- `generate_audio`: requests speech or music and returns its URL.
- `check_balance`: reports the Pollinations balance.
- `generate_batch`: creates up to 10 images in one request.

The repository also documents a separate REST API for programmatic access. Its endpoints cover generation, model listing, balance checks, and an OpenAPI schema, but that API is distinct from the MCP tool interface.

## Limitations and notes

doctor m333/promptpilot-mcp-server depends on Pollinations for the underlying media generation. Paid-model access depends on a valid Pollinations API key and available credits. Generated results are exposed as URLs, so clients or downstream workflows must handle retrieving or presenting those URLs. Batch generation is limited to 10 images per call.

_Full upstream README: https://allmcps.com/mcp/doctorm333-promptpilot-mcp-server/readme_