promptpilot-mcp-server
Enables text-to-speech generation using ElevenLabs models to create high-quality audio and speech directly from AI agents.
PromptPilot MCP Server
Generate images, video, and audio directly in Claude Code, Cursor, Windsurf, or any MCP-compatible AI agent.
20+ models — Flux, GPT-Image-1, Imagen 4, Grok Imagine, Seedance, ElevenLabs TTS, and more. Free models work without an API key. Paid models require a Pollinations key.
Installation
Claude Code / Claude Desktop
{
"mcpServers": {
"promptpilot": {
"command": "npx",
"args": ["-y", "promptpilot-mcp"]
}
}
}With Pollinations API key (for paid models):
{
"mcpServers": {
"promptpilot": {
"command": "npx",
"args": ["-y", "promptpilot-mcp"],
"env": {
"POLLINATIONS_API_KEY": "sk_your_key_here"
}
}
}
}Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"promptpilot": {
"command": "npx",
"args": ["-y", "promptpilot-mcp"]
}
}
}Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"promptpilot": {
"command": "npx",
"args": ["-y", "promptpilot-mcp"]
}
}
}VS Code (GitHub Copilot)
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"promptpilot": {
"type": "stdio",
"command": "npx",
"args": ["-y", "promptpilot-mcp"]
}
}
}Docker
docker run -i --rm \
-e POLLINATIONS_API_KEY=sk_your_key_here \
mcp/promptpilot-mcpRelated MCP server: Photo AI Studio MCP Server
Tools (8 total)
Tool | Description |
| List all image/video/audio models with pricing |
| List styles, lighting, camera, mood, color presets |
| Build optimized prompt from structured inputs |
| Generate image (returns URL) |
| Generate video (returns URL) |
| Generate speech or music (returns URL) |
| Check Pollinations API balance |
| Generate up to 10 images in one call |
Examples
Generate an image:
"Generate a cyberpunk cityscape at night using the flux model"
Batch generation:
"Generate 5 product photos with different backgrounds"
Build + generate:
"Build me a portrait prompt with dramatic lighting and golden hour mood, then generate it"
Check what's available:
"What video models do you have and what are their prices?"
REST API
PromptPilot also offers a REST API for programmatic access from any language:
# Get your token at https://promptpilot.club/profile (REST API tab)
curl https://promptpilot.club/api/v1/generate \
-H "Authorization: Bearer pp_your_token" \
-H "Content-Type: application/json" \
-d '{"prompt": "red panda in bamboo forest", "model": "flux", "fields": "url,model"}'Endpoints:
POST /api/v1/generate— generate image/video/audioGET /api/v1/models— list models with pricesGET /api/v1/balance— check balanceGET /api/v1/schema— OpenAPI schemaGET /api/v1/AGENT_CONTEXT.md— quick reference for agents
Links
promptpilot.club — Web UI
Pollinations AI — Underlying model provider
License
MIT
Available Tools
8 toolsbuild_promptB
Build an optimized prompt from subject + style/lighting/camera/mood/color/quality options
Inputs: subject (required), style, lighting, camera, +3 more.
check_balanceA
Check your Pollinations API balance (pollen). Shows remaining credits for paid models.
Inputs: no named parameters.
generate_audioC
Generate audio (speech or music) using Pollinations API. Returns a URL to the generated audio.
Inputs: prompt (required), model, voice.
generate_batchB
Generate multiple images in one call (up to 10). More efficient than calling generate_image repeatedly.
Inputs: prompts (required).
generate_imageC
Generate an image using Pollinations API. Returns a URL to the generated image.
Inputs: prompt (required), model, width, height, +2 more.
generate_videoC
Generate a video using Pollinations API. Returns a URL to the generated video.
Inputs: prompt (required), model, aspect_ratio, duration, +1 more.
list_modelsB
List all available models for image, video, and audio generation with their type and pricing
Inputs: no named parameters.
list_stylesB
List all available styles, lighting, camera angles, moods, colors, and quality tags for prompt building
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose with no overlap: build_prompt constructs prompts, check_balance checks API credits, generate_* tools create different media types, and list_* tools provide metadata. The separation between generate_image, generate_batch, generate_video, and generate_audio is unambiguous, and list_models vs list_styles serve different informational needs.
All tools follow a consistent verb_noun naming pattern with snake_case throughout. The verbs are descriptive and appropriate: build_, check_, generate_, and list_ are used consistently across related tools, making the set predictable and easy to understand at a glance.
With 8 tools, this server is well-scoped for its purpose of interacting with the Pollinations API for media generation and prompt building. Each tool earns its place by covering distinct aspects: prompt construction, balance checking, media generation (with batch optimization), and model/style listing, without being overwhelming or insufficient.
The tool set covers core workflows comprehensively: prompt building, credit management, media generation (image, video, audio, batch), and resource listing. A minor gap is the lack of tools for managing generated content (e.g., delete or retrieve metadata), but agents can work around this using the provided URLs and API balance checks.
Maintenance
Related MCP Connectors
Create images & video from any MCP agent — 17 models, spend limits, one URL.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models and 10 tools: up to 4 images per call, SVG vectorization, editing and more. Remote MCP with OAuth, no API keys. Pay per image, no subscription.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceGenerate videos, images, audio, and 3D models from any MCP-compatible AI agent — Claude, Cursor, ChatGPT, and more.MIT- AlicenseAqualityCmaintenanceEnables AI photo generation, editing, and video creation from MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.87 npmMIT
- AlicenseNot gradedqualityDmaintenanceFree, keyless image generation MCP server that lets AI agents create images from text prompts via Pollinations/Flux. Supports multiple aspect ratios and returns local image file paths.MIT
- AlicenseNot gradedqualityCmaintenanceGenerate AI images and videos from Claude, Cursor or any MCP client: 48+ models on one account (Flux 2, Nano Banana 2, Seedream 5, Kling V3, Seedance 2.5, Veo 3.1), with the exact cost in credits returned on every call.1MIT