Provides image and video generation using Google AI Pro/Ultra accounts, including Nano Banana and Veo 3.1 through Google Flow and Gemini, with sign-in and status checks.
Provides image generation through ChatGPT (GPT Image) using a ChatGPT Plus/Pro account, either via the Codex CLI or chatgpt.com sign-in, with account status and credit checks.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@no-api-media create a 16:9 hero image for our landing page, match the site's style"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server that makes images and videos for your projects with the AI subscriptions you already pay for. No API keys. No second bill. Uses your own ChatGPT, Google AI Pro, Higgsfield and Grok accounts.
Features • Quick start • Connect accounts • Installation • Tools • CLI commands • Troubleshooting
Images and videos from your own plans: GPT Image (ChatGPT via Codex), Nano Banana and Veo 3.1 (Google Flow), Gemini, Higgsfield (Seedance, Kling and more), Grok
No API keys at all: you sign in once, by hand, in a private Chrome window. API-key variables are stripped before any tool runs
Understands your project: reads its colours, fonts, 3D or animation libraries and existing images, then matches the style (luxury, premium, playful, corporate, modest)
Designer-grade prompts: three concept directions per asset with a critique checklist, so results aren't generic
Saves straight into your project: full quality, no Download folder, no Save dialog, never outside the project
Shrinks for the web without visible loss: WebP and H.264, checked with an SSIM quality score
Credit-safe: shows the cost first, hard max_credits cap, one job at a time
Add any site with a small JSON file, no code
Related MCP server: img-vid-mcp
git clone https://github.com/farhan6667/no-api-media-mcp
cd no-api-media-mcp
npm install && npm run build
node dist/src/index.js setupsetup checks your machine, opens a Chrome window where you sign in to ChatGPT and Google, and prints the line to add to your AI client. Then ask your agent:
Use no-api-media to make a 16:9 hero image for this site with flow. Check the project's style first.
You sign in yourself, once. The server never asks for or sees a password.
Account | You need | How to connect | Ready when |
Google AI Pro / Ultra (Flow, Gemini) | A Google account with the plan | Sign in at the Google tab in the setup window |
|
ChatGPT (images) | ChatGPT Plus or Pro |
|
|
Higgsfield | A Higgsfield plan |
|
|
Grok or any JSON site | That site's plan | Ask your agent to run |
|
Close the whole setup window when you're done. The server can't use the private profile while it is open.
Requirements: Node 22+, Google Chrome, and ffmpeg for shrinking files.
# all projects
claude mcp add --scope user no-api-media -- node /full/path/to/no-api-media-mcp/dist/src/index.js
# this project only
claude mcp add no-api-media -- node /full/path/to/no-api-media-mcp/dist/src/index.jsAdd to your MCP config:
{
"mcpServers": {
"no-api-media": {
"command": "node",
"args": ["/full/path/to/no-api-media-mcp/dist/src/index.js"]
}
}
}Config file locations:
App | File |
Claude Desktop (Windows) |
|
Claude Desktop (macOS) |
|
Cursor |
|
Windsurf |
|
Restart the app after editing.
.vscode/mcp.json:
{
"servers": {
"no-api-media": { "command": "node", "args": ["/full/path/to/no-api-media-mcp/dist/src/index.js"] }
}
}codex mcp add no-api-media -- node /full/path/to/no-api-media-mcp/dist/src/index.jsTool | What it does |
| Opens the private Chrome window so you sign in |
| Which accounts are ready, plan tier, low-credit warnings |
| Every provider and JSON site, and what each can make |
| Reads the project: style tier, 3D/animated, colours, fonts, reference images |
| Art direction: concept directions with ready prompts and a critique checklist |
| Makes images with |
| Exact credit cost for a Flow or Higgsfield job, generates nothing |
| Veo 3.1 / Omni in Flow, Seedance / Kling in Higgsfield, or Grok, with a credit cap |
| Image to WebP, video to H.264, smaller with no visible change |
id | Makes | Signs in with | Notes |
| images | Codex CLI, ChatGPT login | Most reliable ChatGPT route |
| images | chatgpt.com in the private profile | Cloudflare may ask for a human check; use |
| images, videos | Google, in the private profile | Nano Banana 2 images were 0 credits on AI Pro when tested; videos cost credits |
| images | Google, in the private profile | |
| images, videos | official CLI (OAuth) | Exact cost shown before every job |
| images, videos | grok.com in the private profile | Limits depend on your plan |
No output_path: <project>/.ai-media/<provider>/<date>-<prompt>.<ext>, ignored by git, with a manifest.jsonl of every prompt
With output_path (e.g. public/images/hero.png): must be inside the project and a media file, checked before anything is generated
Command | What it does |
| Check everything, open the sign-in window, print client config |
| Sign in to one service again ( |
| Show which accounts are ready, without opening a window |
| Print the version |
| List these commands |
| Check the Codex CLI is signed in with ChatGPT |
| List Higgsfield workspaces to pick one |
| Run the test suite (unit and security tests) |
Without a command, dist/src/index.js runs as the MCP server. That's what your AI client starts.
You see | Do this |
| The sign-in window (or another copy of the server) is still open. Close that Chrome window and try again |
| Run |
| ChatGPT's Cloudflare noticed automation. The server never solves these. Use |
| Run |
| Your plan's Codex quota is spent. Use |
|
|
| Sign in with the account that has your AI plan, or set |
| Google changed the Flow page. Update to the latest version or open an issue |
| Video credits are low. Images on Nano Banana 2 usually still work |
| Install Chrome or set |
|
|
| Use a path inside the project, like |
Nothing happens on a Linux server | Chrome needs a display. Run under Xvfb |
All optional.
Variable | Default | Meaning |
|
| Private profile and state. Delete it to sign out of everything |
| the folder the client starts the server in | Folders the server may write to |
| first signed-in account | Which Google account to use |
|
| Seconds between two generations on one provider |
| auto-detected | Binary locations |
Put a file in ~/.no-api-media/providers/<id>.json. Start from examples/providers/template.json. Media is only downloaded from the hosts you list in mediaHosts, and specs are never read from a project folder.
Your password never touches this code, there is no network port, and the server can't write outside your project. The full threat model is in SECURITY.md.
Web providers drive the consumer sites the way you would by hand. OpenAI's, Google's and xAI's terms restrict automated use of those sites, so using them is your call and your account's risk. The server works at human pace, stops at captchas and sign-in pages, and doesn't hide that it is automation. Official CLIs (Codex, Higgsfield) are the safer routes.
Fixes for broken selectors and new site specs are the most useful help. See CONTRIBUTING.md.
Built by Syed Farhan Ahmed · nexaforge.eu.cc · LinkedIn · Portfolio
This server cannot be deployed
Image and video AI tools and your own pipelines, run from any AI assistant.
Sync Lightroom, Figma, Dropbox & Canva assets to WordPress and Shopify via natural language.
Sync Lightroom, Figma, Dropbox & Canva assets to WordPress and Shopify via natural language.
Generate images, video, music and voice from your CLI or AI agent. On-brand AI media toolkit.
