This connects Claude to Flux, Veo 3.1, and Suno V5 for generating images, videos, and music directly from agent workflows. You get cost estimation before execution, hard budget controls via a reserve/burn/refund model, and tools like generate_image, generate_video, generate_music, plus editing ops like upscale, inpaint, and background removal. It runs as a remote MCP server over streamable HTTP, so no local setup. Includes a free tier for testing and supports OAuth 2.1 for enterprise deployments. Reach for this when you need production media generation with predictable pricing and want agents to handle creative tasks without manual API wrangling.
Agent-native AI platform for AI Room, Media API, and Coding Plan API.
Website | Developer Hub | AI Room | Dashboard | Status
Conversational creative workspace where custom-trained AI agents use session context to create images, video, voice, and music.
Unified generation API for image, video, and music workflows. Current public model surfaces include Pimo AI-Video, Aura Image Turbo, and Pira V5.5.
https://api.vapagent.com/api/v1POST /api/v1/generationsPOST /api/v1/operationshttps://api.vapagent.com/mcpOpenAI-compatible API for coding agents, IDEs, editors, and automation workflows. Powered by Nemesis Deep Coder with model ID vap-code.
https://api.vapagent.com/v1vap-codePOST /v1/responsesPOST /v1/chat/completionsUse these entry points for new integrations:
| Need | Link |
|---|---|
| Use AI Room | https://vapagent.com/new |
| Generate a Media API key | https://vapagent.com/developer/?key=media#keys |
| Generate a Coding Plan API key | https://vapagent.com/developer/?key=code#keys |
| View Coding Plan API plans | https://vapagent.com/new-dashboard/?billing=code#plans |
| Read Developer Hub | https://vapagent.com/developer/ |
| See Nemesis Deep Coder | https://vapagent.com/models/nemesis-deep-coder.html |
This repository remains the public GitHub and MCP discovery surface for VAP Media API integrations. MCP is still supported for Claude Desktop, Claude Code, Cursor-compatible MCP clients, and other agent workflows that call VAP media tools.
Claude Desktop example:
{
"mcpServers": {
"vap": {
"url": "https://api.vapagent.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_MEDIA_API_KEY"
}
}
}
}
For clients that do not support headers directly, use the local proxy in mcp/vap_mcp_proxy.py and set VAP_API_KEY.
curl -X POST https://api.vapagent.com/api/v1/generations \
-H "Authorization: Bearer YOUR_MEDIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"kind":"image","prompt":"a neon city at night"}'
curl -X POST https://api.vapagent.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_CODING_PLAN_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"vap-code","messages":[{"role":"user","content":"Review this patch."}]}'
Use these current public contracts from Developer Hub:
https://api.vapagent.com/api/v1POST /api/v1/generationsPOST /api/v1/operationshttps://api.vapagent.com/mcphttps://api.vapagent.com/v1server.json: MCP Registry server metadatamcp.json: MCP package metadataglama.json: Glama MCP listing metadatamcp/tools.json: MCP tool schema metadatamcp/vap_mcp_proxy.py: local stdio/http proxy for MCP clientsMIT License. See LICENSE.
miapre/html-to-figma-design-system
ie3jp/illustrator-mcp-server
coding-solo/godot-mcp
ivanmurzak/unity-mcp
yctimlin/mcp_excalidraw
figma/mcp-server-guide