AI Video Check

net.aivideocheckv1.0.0Updated Oct 1, 2026

Check whether a video was generated by AI (Sora, Veo, Kling, HeyGen and others).

VerifiedStreamable HTTPWeb executableAI & MLMedia & Design

Overview

AI-generated overview

Lets an assistant submit a video link or local file to AI Video Check and get a probability score for whether it was AI-generated.

What it does
Connects an MCP client to the AI Video Check detection service. The check_video tool takes a public link (TikTok, Instagram, X, YouTube, Facebook or a direct file URL) and returns a probability of AI generation with separate scores for picture and sound; check_file does the same for a video on the user's own computer in local mode. get_check retrieves an earlier result, kept for 24 hours, and get_balance shows remaining credits and key limits.
When to use it
Useful when an assistant needs to assess whether a video is likely AI-generated, for example while reviewing social media clips or user-submitted media. Results are probabilities, not proof, and editing, visual effects or face swaps on real footage are not detected.
Requirements
A remote Streamable HTTP endpoint at or the local Python server for checking files on disk. An AI Video Check account and API key are required, sent as a Bearer token in the Authorization header (remote) or via the AVC_API_KEY environment variable (local). Network access is needed; checks consume credits.
Before you install
The API key is a secret: anyone holding it spends the account's credits, and it can be revoked from the dashboard. Checks cost one credit per started minute of video, so usage spends real money. In local mode, check_file uploads the selected video file to AI Video Check for analysis; files are deleted when the check ends.

Installation

In SourceWeft

  1. Open AI Video Check in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://api.aivideocheck.net/mcp"
    }
  }
}

README

AI Video Check — MCP server

Let Claude, Cursor or any MCP client check whether a video was generated by AI.

This server connects your AI assistant to AI Video Check, a detector for AI-generated video (Sora, Veo, Kling, MiniMax, HeyGen and others). Give it a link or a local file, and it returns the probability of AI generation with separate scores for the picture and the sound.

It is a thin layer over the public AI Video Check API: the same key, the same credits and the same results.

Tools

ToolWhat it doesCost
check_video(url)Checks the video at a public link (TikTok, Instagram, X, YouTube, Facebook or a direct file URL). Waits up to about a minute for the result.1 credit per started minute of video
get_check(check_id)Returns the result of an earlier check. Results are kept for 24 hours.free
get_balance()Shows the remaining credits and the limits of your key.free
check_file(path)Checks a video file on your own computer. Local mode only.1 credit per started minute of video

Every result tells the assistant how to read it: a probability, not proof. A low score means no signs of generation were found, not that the video is authentic. Editing, visual effects and face swaps on real footage are not detected.

Get a key

  1. Sign in at aivideocheck.net and confirm your e-mail.
  2. Open Dashboard → API and create a key. It is shown once.
  3. Your first key comes with 20 free credits for the API.

Keep the key secret. Anyone holding it spends your credits. You can revoke a key on the same page; it stops working within a minute.

Connect: remote server (links)

The server runs at https://api.aivideocheck.net/mcp (Streamable HTTP). Your client sends the key in the Authorization header.

Claude Code

bash
claude mcp add --transport http aivideocheck https://api.aivideocheck.net/mcp --header "Authorization: Bearer avc_live_..."

Cursor (~/.cursor/mcp.json)

json
{  "mcpServers": {    "aivideocheck": {      "url": "https://api.aivideocheck.net/mcp",      "headers": { "Authorization": "Bearer avc_live_..." }    }  }}

Any other client that supports Streamable HTTP with custom headers works the same way.

Connect: local server (links and files on your computer)

The local server runs on your machine and can also check video files from your disk. It uploads them to AI Video Check for analysis, exactly as the website does; files are deleted when the check ends.

bash
git clone https://github.com/aivideocheck/aivideocheck-mcpcd aivideocheck-mcppython -m venv .venv.venv/bin/pip install -r requirements.txt        # Windows: .venv\Scripts\pip

Then point your client at it, for example Claude Desktop (claude_desktop_config.json):

json
{  "mcpServers": {    "aivideocheck": {      "command": "/path/to/aivideocheck-mcp/.venv/bin/python",      "args": ["/path/to/aivideocheck-mcp/avc_mcp.py"],      "env": { "AVC_API_KEY": "avc_live_..." }    }  }}

check_file sends only files that are named and built like a video container (MP4, MOV, WebM, MKV, AVI and similar). Anything else stays on your computer, so an instruction hidden in a web page cannot make your assistant upload, say, your SSH key.

Configuration

VariableDefaultMeaning
AVC_API_KEY—Your key. Read in local mode only; the remote server never uses a key from its own environment.
AVC_API_BASEhttps://api.aivideocheck.netAPI address.
AVC_MCP_WAIT_S55How long check_video waits for a result before returning the check id.

Development

bash
.venv/bin/python tests/test_mcp.py

The test runs the server against a fake API on 127.0.0.1, over real HTTP and real stdio, with the MCP SDK's own client. It does not touch the live service.

Pricing and terms

Checks spend the same credits as the website: one credit per started minute of video. Prices are on the developer page. Use of the API is governed by the Terms of Service and the Privacy Policy.

Questions: [email protected]

License

MIT — see LICENSE.

Source: README.md at commit 0e05054

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 1, 2026