Generate AI video inside ChatGPT and Claude with the eroq MCP server

You already describe shots to an assistant all day — "give me a slow push-in on a rainy alley, vertical, moody." The render should not require a tab switch. eroq runs a remote MCP server at https://eroq.ai/mcp; connect it once and image, video and speech generation appear inside ChatGPT or Claude as tools the assistant can call. Same account, same wallet, same credit prices as the API and the studio. Nothing new to meter.

What the MCP server is, in one paragraph

The Model Context Protocol is the open standard assistants use to call external tools. eroq's server speaks Streamable HTTP, is stateless, and every tool is a thin client of the public /v1 API — generate_image is POST /v1/images/generations with a friendlier name. If you have used the API, you already know what each tool will do, what it costs and what it refuses.

Sign in instead of pasting a key

Claude, ChatGPT, Claude Code, Cursor and VS Code all connect with a sign-in: the app sends you to eroq, you click Allow, and it receives its own key — listed in your dashboard under Developers → API keys as « Claude (connected) », « ChatGPT (connected) » and so on. Nothing secret is pasted anywhere, and revoking that one key cuts that one app off. The one-click buttons for every app are on eroq.ai/mcp.

Scripts and clients that cannot run a sign-in still authenticate with a key, as a Bearer header:

https://eroq.ai/mcp
Authorization: Bearer eroq_sk_YOUR_KEY

Per-key rate limits apply either way (video and speech at 6 requests a minute on the base tier, multiplied by your plan), which is a comforting property for a key an assistant holds.

Connect Claude (web and desktop)

Press Connect eroq to Claude on eroq.ai/mcp: Claude opens « Add custom connector » with the URL filled in. Click Add, then Connect, sign in to eroq and Allow. The full walkthrough is in how to connect eroq to Claude.

Connect ChatGPT

1. In ChatGPT's settings, turn on Developer mode (web; Plus, Pro, Business, Enterprise, Edu).
2. Create an app named eroq with the MCP server URL https://eroq.ai/mcp and OAuth as the authentication.
3. Sign in to eroq, click Allow, and pick eroq from the composer's developer-mode tools.

Details and troubleshooting: how to use eroq in ChatGPT.

Claude Code takes one line, then /mcp → Authenticate:

claude mcp add --transport http eroq https://eroq.ai/mcp

The tools

• generate_image — text or reference to image; waits for the render and returns the picture plus a link. 10 credits on Krea 2 — every image model lists its price. A slow cold start hands back a job id for get_image_status (free).
• generate_video — starts an async render and waits briefly; if the clip is not done yet it hands back a job id.
• get_video_status — free; polls that job id. Failed jobs refund themselves.
• generate_speech — text-to-speech MP3; roster voices, your clones, or char:<id> to speak as one of your characters.
• enhance_prompt — free with any plan; turns a rough draft into an engine-grade image or video prompt, or invents one when you give it nothing.
• list_models — free; every model with its credit price, availability and plan gate.
• list_voices, list_characters, get_account — free; the roster, your cast, and the wallet.

Every render also lands in your Library with its full recipe, so a clip made from a chat can be remixed in the studio later.

A sample conversation

Here is roughly what a session looks like. The assistant decides which tool to call; you talk in plain language.

You:  I need a vertical teaser for a short film about a lighthouse keeper.
      Tighten this into a real prompt first: "keeper climbs the stairs at night, storm".

AI:   [enhance_prompt kind=video]
      "A lighthouse keeper in a yellow raincoat climbs the spiral stairs of a
      stone lighthouse at night, lantern swinging, slow tracking shot following
      her up, warm practical light against cold blue storm windows, rain streaks
      on the glass, tense, patient mood, 35mm film grain."

You:  Good. Render it, 10 seconds, 9:16, on Motion One.

AI:   [generate_video model=eroq-motion-one seconds=10 aspect=9:16]
      Started — job b7e6c2d4. Rendering usually takes one to five minutes.

You:  Check on it.

AI:   [get_video_status id=b7e6c2d4]
      Done. Clip: https://…/library/…/b7e6c2d4.mp4 — 290 credits spent, 1,720 left.

Two things to notice. enhance_prompt is free with any plan, so use it liberally; the rewritten prompt names subject, motion, camera, light and mood in one paragraph, which is what the engines like. And generate_video is honest about time: it does not pretend a two-minute render finished in ten seconds. Ask again, or let the assistant poll.

The same flow works for stills — "make me a poster frame of that keeper on Krea2, 3:4" — and for voice — "read the logline with Orion, slower."

What it costs

New accounts get 40 free credits: a few stills, or one five-second Motion One clip at 480p (35 credits), enough for a quick test of the tools. After that, prices are the flat ones on the pricing page:

• Images: from 10 credits each, depending on the model.
• Motion One: 145 credits for 5 s, 290 for 10 s, on every account. It is also the uncensored video engine; the third-party engines (Seedance, Kling, Hailuo, Veo and the rest) are moderated upstream by their providers, and all but Seedance 2.0 Mini and Veo 3.1 Lite need a Hobby or Creator plan.
• Speech: 3 credits per 100 characters on Voice One, 2 on Voice Turbo.
• enhance_prompt (free with any plan), list_models, list_voices, list_characters, get_account and get_video_status: free.

Charges happen before the engine runs and refund themselves if the render fails. A request outside the acceptable-use policy returns content_blocked and is never charged. An empty wallet answers HTTP 402 — the assistant will tell you, not fail silently.

One policy note. The assistant you are talking to applies its own usage rules to what it is willing to write and send; eroq's policy applies to what renders: fiction only; nothing involving minors, no real identifiable people without consent, nothing illegal.

FAQ

Does the connector work on the free tier?

Yes. The 40 welcome credits, Motion One, eroq's own image models, every voice and text model, clips up to 10 seconds. Premium video and image engines and longer clips are plan-gated.

Do I need an API key for the connector?

No. Claude and ChatGPT sign in with your eroq account and get their own key, which you can revoke from the dashboard without touching anything else.

Why did generate_video give me a job id instead of a clip?

Video takes one to five minutes and the tool only waits briefly. The job id is your receipt: get_video_status is free and returns the clip when it is done — or the refund if it failed.

Ready to try it? Connect eroq to Claude or ChatGPT in a couple of minutes.