AI Video Checker MCP server
Which servers in the official MCP registry are AI Video Checker's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namenet.aivideocheck/mcpverified in the MCP registry
The registry name sits under aivideocheck.net. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools3
- Server calls itselfAI Video Check
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 490 ms.
- Its tools do every use case we checked: Check a public TikTok, Instagram, YouTube or X link; Get a probability score for a suspect video.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- For "Check a public TikTok, Instagram, YouTube or X link", the likely first call is check_video.
- For "Get a probability score for a suspect video", the likely first call is check_video.
- Parameters are untyped or undescribed in 2 of 3 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- What an agent can do with it2 of 2 use cases
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer511 ms
- Space in an agent's context≈ 239 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsB · 89 of 100
- Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 3
What an agent can do with it
- not sure · Check an uploaded video file for AI generation
- can do · Check a public TikTok, Instagram, YouTube or X link
- can do · Get a probability score for a suspect video
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
check_videoCheck whether the video at a public link (TikTok, Instagram, X, YouTube, Facebook or a direct file URL) was generated by AI. Spends credits: one per started minute of video. Waits up to about a minute; if the check is not done by then…
get_checkGet the status or result of an earlier check by its id. Free. Results are kept for 24 hours.
get_balanceShow how many AI Video Check credits the account has left and the limits of its key. Free.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"aivideocheck": {
"type": "http",
"url": "https://api.aivideocheck.net/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http aivideocheck https://api.aivideocheck.net/mcpclaude.ai, ChatGPT and other clients: add https://api.aivideocheck.net/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.