fal.ai

fal.ai is a generative media platform for developers to run hosted AI models, deploy serverless model endpoints, and manage related assets, usage, and compute resources. It supports image, video, audio, workflow, and real-time inference use cases.

4 integrations · MCP · REST · CLI

fal.ai exposes authenticated HTTP Model APIs and Platform APIs, a hosted MCP server, and a Python-installed `fal` CLI.

discovered 2mo ago

MCP servers1

fal MCP serverdetectedstreamable-http

REST · OpenAPI2

fal Model APIsdiscoveredrest
fal Platform APIsdiscoveredrest

CLI1

fal CLIdiscoveredfal

Credentials

OAuth 2.0oauth2

OAuth 2.0 — self-onboarding

Point your MCP client at the server URL and approve access in the browser. The server supports OAuth Dynamic Client Registration (RFC 7591), so the client registers itself automatically — no developer-portal app, client_id, or client_secret to create.

fal CLI interactive loginoauth2$ fal auth login

Acquired by the CLI — running fal auth login opens the auth flow and stores the credential.

conventions · 1/7 published

integrations.json——
llms.txt✓https://fal.ai/llms.txt
API catalog✗/.well-known/api-catalog
OpenAPI document✗/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json
MCP server card✗/.well-known/mcp/server-card.json
OAuth protected resource✗/.well-known/oauth-protected-resource
Agent card✗/.well-known/agent-card.json
Agent skills✗/.well-known/agent-skills/index.json

Publish these signals → /publishing