MCP server by fal · vendor-hosted · maintained
Official fal-hosted MCP relay. Discover, run and chain 1,000+ generative AI models (image, video, audio) via OAuth over Streamable HTTP at mcp.fal.ai/mcp-relay.
Choose your AI client and copy the config.
Remote MCP — add to claude_desktop_config.json (or Connectors). Clients without native remote support can use the mcp-remote bridge below. Setup guide
{
"mcpServers": {
"fal": {
"url": "https://mcp.fal.ai/mcp-relay"
}
}
}stdio bridge (mcp-remote):
{
"mcpServers": {
"fal": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.fal.ai/mcp-relay"
]
}
}
}Add to ~/.cursor/mcp.json or .cursor/mcp.json, then complete OAuth when prompted. Setup guide
{
"mcpServers": {
"fal": {
"url": "https://mcp.fal.ai/mcp-relay"
}
}
}Add to .vscode/mcp.json (HTTP transport). Setup guide
{
"servers": {
"fal": {
"type": "http",
"url": "https://mcp.fal.ai/mcp-relay"
}
}
}Cascade → MCP servers → Add custom server. Setup guide
{
"mcpServers": {
"fal": {
"url": "https://mcp.fal.ai/mcp-relay"
}
}
}Run in your terminal, then /mcp to authenticate: Setup guide
claude mcp add --transport http fal https://mcp.fal.ai/mcp-relayCLI or add to ~/.codex/config.toml. Setup guide
codex mcp add fal --url https://mcp.fal.ai/mcp-relay[mcp_servers.fal]
url = "https://mcp.fal.ai/mcp-relay"Use the mcp-remote bridge if the client is stdio-only. Setup guide
{
"mcpServers": {
"fal": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.fal.ai/mcp-relay"
]
}
}
}ChatGPT web needs a remote HTTPS MCP URL (Plugins → Add custom MCP server). Setup guide
https://mcp.fal.ai/mcp-relayVendor-hosted Streamable HTTP endpoint (OAuth on first connect):
https://mcp.fal.ai/mcp-relayLocal-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
lightweight Python-based MCP (Model Context Protocol) server for local ComfyUI
Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.
End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and TTS.