
Falai
io.usefulapiv1.0.0Updated Sep 29, 2026
Run fal.ai models, poll the inference queue and read model schemas.
Overview
Lets an assistant run fal.ai generative models, submit and poll inference requests, and read model schemas through a hosted endpoint.
- What it does
- This hosted MCP server exposes fal.ai model operations as tools. Read tools list models, fetch a model's schema, and check the status or result of a request. Write tools submit a request, run a model with subscription-style polling, and cancel a request.
- When to use it
- Useful when an assistant needs to generate images, video, audio, or other outputs from fal.ai models, or to inspect available models and their input schemas before calling them. It fits workflows where inference is triggered and then polled to completion.
- Requirements
- A remote MCP endpoint at no local install or package. On first connect you paste your fal.ai credentials, which are validated and stored per user. Network access to the endpoint is required.
Installation
In SourceWeft
- Open Falai in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"falai": {
"type": "http",
"url": "https://falai.usefulapi.io/mcp"
}
}
}README
fal.ai MCP by usefulapi
Run fal.ai models, poll the inference queue and read model schemas. Hosted, no local install.
Live endpoint: https://falai.usefulapi.io/mcp · Homepage: https://usefulapi.io
Add to Claude
On first connect you'll paste your fal.ai credentials. They are validated, stored per-user, and scoped to you — no keys in config files.
Tools
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage or manage your subscription.
Pricing
License
MIT
Source: servers/falai/README.md at commit e28f9c1
Tools
0Version history
1- v1.0.0LatestSep 29, 2026
