Skip to main content
Glama

Check if video frames or media were AI-generated

detect_ai_media

Analyze 1–6 still frames from a video (or a single image) for signs of AI generation (Sora, Veo, Kling, Runway, Seedance, etc.) vs. real camera footage, returning likelihood (low/medium/high), 0–100 score, summary, AI artifacts and real-footage signs. Uses 1 check.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "detect_ai_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
markersNoOptional container metadata markers such as "c2pa" or encoder tags.
durationNoOptional video duration in seconds.
image_urlNoPublic https URL of a single JPEG, PNG or WebP image (up to 5 MB).
image_urlsNoOptional list of public https URLs of still frames sampled from one video (1–4 for locate_media, 1–6 for detect_ai_media).
image_base64NoBase64-encoded JPEG, PNG or WebP image (with or without data: prefix).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (openWorldHint=true, destructiveHint=false), the description discloses the credit cost ('Uses 1 check') and enumerates the returned fields (likelihood low/medium/high, 0–100 score, summary, AI artifacts, real-footage signs). It does not cover failure modes, whether the frame count changes cost, or why readOnlyHint is false for a purely analytical call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that packs inputs, detection scope, return values and cost with no filler. It is dense to the point of being a run-on, and the parenthetical list of generators is mildly decorative, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With full schema coverage and no output schema, the description covers the essentials: what goes in, what comes back, and the credit cost. Remaining gaps are minor—input-mode precedence and error/edge behavior—for an otherwise simple analysis tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters are already documented, and the description adds only the mode relationship between a single image and 1–6 sampled frames. It does not explain precedence when both image_url and image_urls are supplied, or how markers and duration influence the verdict.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Analyze 1–6 still frames ... for signs of AI generation') and scopes the input (frames from a video or a single image) and the competing generator families it detects. The operation is clearly distinguishable from locate_media and get_credits, but no sibling is named explicitly, so it stops short of full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the tool for judging AI-generated vs. real footage, and 'Uses 1 check' hints at cost. There is no explicit when-to-use/when-not guidance, no statement about choosing image_url vs. image_urls, and no routing to alternatives such as locate_media for frame extraction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources