toolfare

Ask your AI to run the exact image or video model you want.

Run a specific image or video generation model hosted on fal — by its model id, with that model’s own inputs — and read back runs that are still in progress, answered inside ChatGPT, Claude, Codex or Cursor. No fal account or key of your own: toolfare runs each generation and tells your AI the price before it starts.

Start Asking For FreeConnect in 1 Click

Set it up in

Claude CodeCodexCursorVS CodeChatGPTClaude (web & desktop)Your own agent
toolfare

Sign in, grab the setup prompt from your console, paste it to your agent, ask something. That’s the whole setup.

toolfare research stack

traffic, SEO, app-store and ads intelligence

fal.ai

Run named image and video generation models

Seedance

ByteDance text- and image-to-video, up to 1080p

Creatify

Video ads from a product link or a script

200+

APIs

40+

apps

30+

skills

Ask once, let the agent choose the right source, and see the price before a paid data call runs.

No vendor keyQuoted per callOne research stack
About five minutes

Set it up once, in the app you already use.

There is nothing to install for fal.ai specifically. One connection reaches every source in the catalogue, and this is one of them.

Claude Code

Use the MCP connection in your AI app, or run the toolfare CLI in its terminal. Both use browser approval, discover capabilities and quote paid calls before they run.

  1. 1

    Create your toolfare workspace

    The connection is public and identical for everyone — your toolfare sign-in is what points it at your data. Connect one account in that workspace too: that is what your AI reads. The first time your AI uses the connection, toolfare asks you to approve the access and names the workspace it will read through. No workspace yet? toolfare has you create one right there, then brings you back to approve.

    Create your workspace

    Already have one? Nothing to do here — sign in when the connection asks for it.

  2. 2

    Copy the toolfare MCP connection

    https://api.toolfare.ai/mcp
  3. 3

    Add it to Claude Code

    claude mcp add --transport http toolfare https://api.toolfare.ai/mcp
    1. Run the command in any project. It writes the configuration and prints an `Added …` line.
    2. Authorize separately — adding a server does not open a browser.
    3. Run `claude mcp list` to confirm the server reads `✔ Connected`.
  4. 4

    Approve the access, then ask it something

    1. Inside Claude Code, run `/mcp` and follow the browser flow — or, from your shell, `claude mcp login toolfare`.
    2. The toolfare consent page names the host, the workspace the grant will read through, and what the connection will be able to do.
    3. Approving creates the grant listed above on this page. Cancelling creates nothing.
    4. On a machine with no browser (SSH, headless Linux), `claude mcp login toolfare --no-browser` prints the URL and takes the pasted callback.

    Paste this first

    Using toolfare, search for what capabilities I can reach.

    A list of capabilities with names, what each reads and what each costs. An empty list means the search matched nothing — try broader words. An error naming authorization means the host never completed the browser step.

Checked 2026-08-25 against Claude Code documentation. Menu names change between releases — look for connectors, apps, tools or integrations.

Open the console to connect your accounts
3 things you can ask it

Ask in plain English. These are the tools behind the answer.

Each one is a tool your AI is offered by name once you connect. You never have to type the name — it is here so you can tell what actually ran.

  • Run a named generation model

    fal_run_model

    Invokes one model on fal by its id, with that model’s own input schema, and returns what it produced — or a queue position when it is still running.

    • “Generate a product shot with this image model on fal.”
    • “Make a five-second video from this image with a fal video model.”

  • Collect a run that was still going

    fal_get_queue_result

    Fetches the result of a run that returned a queue position instead of an image or video.

    • “Is that video generation finished yet?”
    • “Get the result of the run I started earlier.”

And 1 more, same connection

Named rather than worked through — your AI discovers all of them through the connection itself, so you never have to pick one.

  • Check whether a queued fal run has finishedfal_get_queue_status
Pricing

Buy toolfare credits for your research and agent workflow.

Pay as you go. Buy credits when you need them, with no subscription.

Pay as you go

10,000 credits from $30

Buy credits when you need them. No subscription. Every paid call is quoted before it runs.

Buy credits