Get started

Fal.ai for AI agents

Fal.ai is a generative media platform giving developers access to hundreds of AI models for image, video, voice, and audio generation. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Fal.aiSee the 12 actions ↓
AI and modelsAPI keyMCP + RESTfal.ai
AUDIT LOG · FAL.AIPOLICY: acme-support
09:41:07 · claude · u_8f2read
fal_ai.get_jwks
Get JWKS for Webhook Verification✓ allowed · 212ms
09:41:08 · claude · u_8f2read
fal_ai.get_models
Get Models✓ allowed · 164ms
09:41:09 · claude · u_8f2write
fal_ai.upload_file
Upload Input File✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
fal_ai.cancel_queue_request
Cancel Queue Request✕ blocked · policy: deny
EVERY FAL.AI CALL, ON THE RECORD
01 · USE CASES

What agents do in Fal.ai.

01

Run a model on new input

Run a chosen model synchronously to generate an image or audio clip from a user's prompt.

02

Check a queued job's status

Check the status of an async inference job before notifying the user it is ready.

03

Check pricing before a large job

Estimate pricing for a model run before submitting a batch job that could use many credits.

02 · ACTIONS

12 Fal.ai actions, graded by risk.

Every Fal.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • fal_ai.get_jwks
    Get JWKS for Webhook Verification
  • fal_ai.get_models
    Get Models
  • fal_ai.get_pricing
    Get Model Pricing
  • fal_ai.get_queue_request_result
    Get Queue Request Result
  • fal_ai.estimate_pricing
    Estimate Pricing

write

6

Create and change things. Allow, or ask the user first.

  • fal_ai.upload_file
    Upload Input File
  • fal_ai.run_model_sync
    Run Model (Sync)
  • fal_ai.queue_get_status
    Check Queue Request Status
  • fal_ai.submit_async_job
    Submit Async Inference Job
  • fal_ai.subscribe_async_job
    Subscribe to Async Inference Job
  • fal_ai.queue_get_status_stream
    Stream Request Status Updates

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • fal_ai.cancel_queue_request
    Cancel Queue Request
03 · HOW IT WORKS

Fal.ai in three steps.

  1. 01Your users connect Fal.aiThey add their Fal.ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “upload Input File” can wait for the user, and “cancel Queue Request” can be denied outright.
  3. 03Any agent can actYour agent calls Fal.ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('fal_ai', {
  read: 'allow',
  write: 'ask',        // upload_file
  destructive: 'deny',  // cancel_queue_request
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Fal.ai connects.

Users add their Fal.ai api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Fal.ai connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Fal.ai from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Fal.ai and Arc0, answered.

Q01

Can I use Fal.ai with Claude, ChatGPT or Cursor?

Yes. Connect Fal.ai to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Fal.ai actions you allow.

Q02

How do users connect Fal.ai?

Users add their Fal.ai api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Fal.ai actions can my agent take?

12 in total: 5 read, 6 write and 1 destructive, such as “upload Input File”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Fal.ai?

Yes. Actions like “cancel Queue Request” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Fal.ai too?

Yes. The same Fal.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Fal.ai into your agent.

Your users connect Fal.ai once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.

Connect Fal.aiBrowse all apps →

Free to build · MCP + REST · Audit log on every plan