Skip to main content
Glama
Sign In

isGenAI

by com.isgenai
OverviewDiscussionsAdmin

Is this image AI-generated? AI image detector

check_image
Read-onlyIdempotent

AI image detector: check an image (PNG, JPEG, WebP, AVIF or single-page TIFF, up to 20 MiB) by public URL or base64. Reads the evidence in the file first (C2PA Content Credentials naming the generator or camera, IPTC AI labels, prompts saved by Stable Diffusion tools, EXIF), then adds an AI-likelihood score from the image detector. Use for: is this photo real or AI, is this a deepfake, was this made with Midjourney, DALL-E, Firefly or ChatGPT? A score is an estimate; records are evidence. No public report is created. Docs: https://isgenai.com/developers/mcp

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": "check_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoPublic http(s) URL. Private network and local addresses are refused.
file_nameNoOriginal file name, if known.
image_base64NoFile bytes as base64 or a data: URL, up to 20 MiB decoded. Prefer url when the file is public.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare safety (readOnly, idempotent, non-destructive), so the description usefully adds the internal process order (embedded C2PA/IPTC/prompt/EXIF evidence first, then the likelihood score), the estimate caveat, and the side effect that no public report is created. Return-value shape is still not described, which matters since there is no output schema.

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?

Front-loaded with purpose, formats and limits, then evidence order, then use cases and caveat. The question-style phrasing ('was this made with Midjourney, DALL-E...?') is somewhat promotional and adds length without operational value, but the structure remains scannable.

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?

For a read-only single-call detector with no output schema, the description conveys the two result layers (evidence records vs likelihood score), the no-report side effect, and a docs link. It stops short of describing the concrete response fields an agent would need to consume results, which is the main remaining gap.

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 coverage is 100%, and the description largely restates it: URL-or-base64 input and the 20 MiB cap are already documented, and the 'prefer url when public' guidance duplicates the schema text. It adds little new parameter meaning, so baseline 3 applies.

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

Purpose5/5

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

States a specific verb and resource ('check an image') plus the detector's nature and accepted formats (PNG, JPEG, WebP, AVIF, single-page TIFF, 20 MiB), which separates it from check_text and check_url by media type and scope. An agent can tell immediately what this tool consumes and returns at a high level.

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

Usage Guidelines4/5

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

The 'Use for:' clause enumerates concrete scenarios (real vs AI, deepfake, Midjourney/DALL-E/Firefly/ChatGPT provenance) and the closing caveat ('A score is an estimate; records are evidence') guides interpretation. It never names a sibling or states an exclusion, so the routing to check_text/check_url/read_content_credentials is left implicit.

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

All isGenAI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources