teamToken Media

Generate images and video with one teamToken account: Veo, Seedance, Kling, Nano Banana, GPT Image and Grok, 51 models in total.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • List Models: List every image and video model with its price. Call this before generating when the user has not named a model, and to check what a model costs: prices are per image for image models an
  • Generate Image: Generate an image and return it. Blocks until the picture is ready (seconds, occasionally up to a few minutes) — do not poll after calling this. To edit or restyle existing pictures, o
  • Edit Image: Edit, restyle or extend existing pictures, or reuse the same character in a new scene. Give the source pictures in `images` (https URLs, data-URLs or bare base64 — one kind per request, do

What data it sees

Do you need an account

No: the server works without sign-in

Generate images and video with one teamToken account: Veo, Seedance, Kling, Nano Banana, GPT Image and Grok, 51 models in total.

Tools

  • list_models shows every model with its price, per image or per second of video.
  • generate_image and edit_image return the picture in the same call.
  • generate_video and extend_video start a job and hand back its ID. get_job fetches the result once it is ready, since video takes minutes rather than seconds.
  • get_balance lets the agent check whether the account can pay for the next run.

Connect

Sign in with your teamToken account when you add the server, or use an API key from app.teamtoken.store. You pay per generation, with no subscription.

How to connect

How to connect teamToken Media to Claude

The server address to paste into Claude settings:

https://teamtoken-mcp--teamtoken.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect teamToken Media to ChatGPT

The server address to paste into ChatGPT settings:

https://teamtoken-mcp--teamtoken.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect teamToken Media to Cursor

The server address to paste into Cursor settings:

https://teamtoken-mcp--teamtoken.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (7)

Raw names from tools/list. Only developers need these.

list_modelsList every image and video model with its price. Call this before generating when the user has not named a model, and to check what a model costs: prices are per image for image models and per second of output for video models. Takes no arguments and spends nothing.
generate_imageGenerate an image and return it. Blocks until the picture is ready (seconds, occasionally up to a few minutes) — do not poll after calling this. To edit or restyle existing pictures, or to keep the same character across images, pass them in `images` and use edit_image instead.
edit_imageEdit, restyle or extend existing pictures, or reuse the same character in a new scene. Give the source pictures in `images` (https URLs, data-URLs or bare base64 — one kind per request, do not mix) and describe the change in `prompt`. Blocks and returns the result, like generate_image.
generate_videoStart a video generation. Returns a job id immediately — video takes 30 seconds to a few minutes, so you MUST call get_job with that id afterwards (wait ~30 seconds before the first check) and keep checking until it reports completed. Do not call this tool again while a job is running: each call costs money.
extend_videoContinue an existing video, adding more seconds to its end. Same asynchronous contract as generate_video: returns a job id to poll with get_job.
get_jobCheck a generation job by its id and get the result when ready. Works for both image jobs (id starts with img_) and video jobs (vid_). While status is queued or processing, wait ~30 seconds and call again.
get_balanceCheck the account balance in USD. Call it before an expensive generation, and after a payment error, so you can tell the user how much is missing.