Add image and video generation to ChatGPT
ChatGPT can call outside tools through its custom MCP connectors. Add Figgshield as one, and ChatGPT can make an image or a short video during a chat using your credits.
Cancel anytime before day 7 · no lock-in
Read this first
Custom MCP connectors in ChatGPT sit behind Developer Mode, which is a beta feature. It is available on the paid plans, so Plus, Pro, Team, Enterprise, and Edu.
On a free ChatGPT account you cannot add a custom connector yet. If you are on a paid plan the setup below takes a couple of minutes.
Turn on Developer Mode and add Figgshield
- In ChatGPT, open Settings, then Connectors, then Advanced settings, and switch on Developer Mode. On Team or Enterprise a workspace admin enables it first.
- Back in Connectors, create a new connector and paste the server URL
https://api.figgshield.ai/mcp. - Sign in with Google when prompted, then pick a plan. The $5 seven-day trial is the quick way in.
- Start a chat and ask ChatGPT to make an image or a clip.
What ChatGPT can make
Images run on Nano Banana 2, which is Google's current image model. Video runs on Kling 3, with a faster Turbo tier when you want a result sooner.
You describe what you want in the chat, ChatGPT sends it to the tool, and the file comes back. You can also give it a reference image to edit from or to animate into a short video.
What it costs
One balance covers both models. An image is 8 credits at 1K or 2K, and 16 at 4K. A five-second Kling clip is 35 credits. Credits are priced at what the models cost us, with no per-image markup. The live credit table lists every option.
Common questions
If Developer Mode is not in your settings, your plan or your workspace has not enabled it. Check that you are on a paid plan, and on a business workspace ask your admin to turn on custom connectors.
Generated files sit on a private link for seven days so you can download them, and then they are deleted. A reference image you send is used in memory and never stored.