Skip to content

fal.ai MCP by usefulapi

by usefulapi.io · remote · no sign-in to list tools · v1.16.3 · published by io.usefulapi

Run fal.ai models, poll the inference queue and read model schemas.

Deletes · 3
CompareRegistry entry

7 tools: 3 can delete or cancel things and 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http falai https://falai.usefulapi.io/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

7 tools

Deletes or cancels 3Claude Code: deny
  • falai_cancel_requestRequest cancellation of a queued (not-yet-started) request.No findings

    Why it is in this group

    • The name "falai_cancel_request" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Request cancellation of a queued (not-yet-started) request. Returns 202 { status: 'CANCELLATION_REQUESTED' }. fal.ai queue: PUT {queue}/{model_id}/requests/{request_id}/cancel.

    Annotations the server declares

    • title: Cancel request
    • destructiveHint: true
  • falai_run_modelConvenience 'subscribe': submit a request, poll its status until COMPLETED, then return the result.No findings

    Why it is in this group

    • The name "falai_run_model" says "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Convenience 'subscribe': submit a request, poll its status until COMPLETED, then return the result. Consumes fal credits. If it does not complete within the wait budget, returns a { status, request_id, status_url, note } object (NOT an error) so you can keep polling with falai_get_request_status / falai_get_request_result.

    Annotations the server declares

    • title: Run model (subscribe)
    • destructiveHint: true
  • falai_submit_requestSubmit an inference request to the queue and return immediately (async — does NOT wait for completion).No findings

    Why it is in this group

    • The name "falai_submit_request" says "submit": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Submit an inference request to the queue and return immediately (async — does NOT wait for completion). Returns { request_id, response_url, status_url, cancel_url, queue_position }. Consumes fal credits when the model runs. fal.ai queue: POST {queue}/{model_id} with body = the model input.

    Annotations the server declares

    • title: Submit request
    • destructiveHint: true
Only reads 4Claude Code: allow
  • falai_get_model_schemaGet the OpenAPI 3 schema for a model — its input/output fields (components.schemas).No findings

    Why it is in this group

    • The name "falai_get_model_schema" says "get": a word for reading.
    Description, as the server wrote it
    Get the OpenAPI 3 schema for a model — its input/output fields (components.schemas). Use this to learn what inputs a model accepts before submitting. fal.ai API: GET /openapi/queue/openapi.json?endpoint_id={model_id}.

    Annotations the server declares

    • title: Get model schema
    • readOnlyHint: true
  • falai_get_request_resultGet the final output of a COMPLETED queued request.No findings

    Why it is in this group

    • The name "falai_get_request_result" says "get": a word for reading.
    Description, as the server wrote it
    Get the final output of a COMPLETED queued request. fal.ai queue: GET {queue}/{model_id}/requests/{request_id}.

    Annotations the server declares

    • title: Get request result
    • readOnlyHint: true
  • falai_get_request_statusGet the status of a queued request (IN_QUEUE | IN_PROGRESS | COMPLETED).No findings

    Why it is in this group

    • The name "falai_get_request_status" says "get": a word for reading.
    Description, as the server wrote it
    Get the status of a queued request (IN_QUEUE | IN_PROGRESS | COMPLETED). fal.ai queue: GET {queue}/{model_id}/requests/{request_id}/status (optional logs=1).

    Annotations the server declares

    • title: Get request status
    • readOnlyHint: true
  • falai_list_modelsList or search fal.ai models in the registry (paginated).No findings

    Why it is in this group

    • The name "falai_list_models" says "list": a word for reading.
    Description, as the server wrote it
    List or search fal.ai models in the registry (paginated). fal.ai API: GET /models (query: keywords, page, total).

    Annotations the server declares

    • title: List models
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.16.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http falai https://falai.usefulapi.io/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__falai__falai_list_models",
      "mcp__falai__falai_get_model_schema",
      "mcp__falai__falai_get_request_status",
      "mcp__falai__falai_get_request_result"
    ],
    "ask": [],
    "deny": [
      "mcp__falai__falai_submit_request",
      "mcp__falai__falai_run_model",
      "mcp__falai__falai_cancel_request"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as falai. Review it before you use it.