Lumethic Photo Verification

verify_content_credentials

Verify a single image's authenticity when the user asks whether it is genuine, AI-generated, manipulated, or carries Content Credentials, and only the image is available (no RAW camera file). Not for feedback on a photo (composition, editing, colour) or for anything that is not a still image. Checks its embedded Content Credentials (C2PA) for capture provenance and AI-generation flags, and runs advisory forensic screens (error-level analysis, double-JPEG artifacts, EXIF timestamp consistency, editing-software traces, screen recapture). Free: it does not consume your verification quota. Provide the image as an attachment (image_file), inline as image_base64, or — for large files without attachments — call create_verification_upload and pass the returned image_object_key. Returns a verification id at once; the analysis runs in the background and takes from about a minute to 10 minutes or more, so call get_verification with the id repeatedly until status is completed; the completed result includes a structured evidence_report (verdict, per-check findings, coverage). For the strongest forensic check, use verify_photo with a RAW + JPEG pair instead.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`image_file`	No	The image (JPEG or PNG) the user attached.
`image_base64`	No	The image as base64, for files up to a few MB. For larger files call create_verification_upload and pass image_object_key instead.
`image_filename`	No	Original image filename with extension. Defaults to the attachment's own name.	upload.jpg
`image_object_key`	No	Object key returned by create_verification_upload for the image.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 8, 2026

addedInput schema / properties / image_file

Added value: +{
+  "default": null,
+  "description": "The image (JPEG or PNG) the user attached.",
+  "properties": {
+    "download_url": {
+      "description": "URL the file can be downloaded from.",
+      "type": "string"
+    },
+    "file_id": {
+      "description": "The client's identifier for the file.",
+      "type": "string"
+    },
+    "file_name": {
+      "description": "Original file name, when known.",
+      "type": "string"
+    },
+    "mime_type": {
+      "description": "MIME type, when known.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "download_url",
+    "file_id"
+  ],
+  "type": "object"
+}

changedInput schema / properties / image_filename / description

Previous value: -"Original image filename with extension."New value: +"Original image filename with extension. Defaults to the attachment's own name."

Changed3 schema fields changedSep 8, 2026

addedInput schema / properties / image_base64 / description

Added value: +"The image as base64, for files up to a few MB. For larger files call create_verification_upload and pass image_object_key instead."

addedInput schema / properties / image_filename / description
```
Added value: +"Original image filename with extension."
```

addedInput schema / properties / image_object_key / description

Added value: +"Object key returned by create_verification_upload for the image."

Changed1 schema field changedSep 7, 2026

removedInput schema / properties / anonymous_user_id

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Anonymous User Id"
-}

First observedJul 25, 2026

TDQS

A4.8/5.0

Behavior5/5

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

The annotations (all false hints) carry almost no behavioral information, so the description rightly carries the full burden. It discloses the async nature ('analysis runs in the background and takes from about a minute to 10 minutes or more'), the immediate id return, the required polling pattern via get_verification, the free/quota trait, and the structured evidence_report shape. These are rich behavioral traits beyond what annotations provide.

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?

The description is long (roughly 8 sentences) but every sentence earns its place for a tool with async behavior and multiple input modes: purpose, exclusions, checks performed, quota, parameter routing, polling, and alternative. It is front-loaded with purpose and scope. Minor redundancy exists ('carries Content Credentials' and later 'embedded Content Credentials (C2PA)'), but overall density is justified.

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

Completeness5/5

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

Given the complexity (4 parameters, 3 input modes, background execution, output schema present), the description is complete: it covers triggering conditions, exclusions, the forensic checks performed, quota impact, polling instructions, and the verified alternative. Since an output schema exists, detailed return-value documentation is not needed. No significant operational gap remains.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds genuine cross-parameter meaning by consolidating the three input paths ('attachment (image_file), inline as image_base64, or — for large files without attachments — call create_verification_upload and pass the returned image_object_key'), which helps an agent choose among the four parameters correctly. This exceeds the baseline without duplicating the schema.

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?

The description states a specific verb and resource: 'Verify a single image's authenticity when the user asks whether it is genuine, AI-generated, manipulated, or carries Content Credentials'. It explicitly scopes to single still images with no RAW file, and names the exclusion ('Not for feedback on a photo... or for anything that is not a still image'), clearly distinguishing it from the sibling verify_photo.

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

Usage Guidelines5/5

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

The description gives explicit when-to-use, when-not-to-use, and alternative routing. It specifies the triggering condition (authenticity question, only image available), the exclusion (photo feedback, non-still images), the stronger alternative ('use verify_photo with a RAW + JPEG pair instead'), and the upload alternative (create_verification_upload for large files). Nothing is left to inference.

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

All Lumethic Photo Verification tools Inspect

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

Need Help?