Skip to main content
Glama

ChronoVerify

by com.chronoverify

Verify image provenance

verify_image
Read-only

Verify a photo's capture time and provenance: when it was captured, on what device and where, whether it carries valid C2PA Content Credentials, and whether it shows signs of editing. Runs a deterministic pipeline (cryptographic C2PA Content Credentials validation against the official trust lists, EXIF and XMP metadata consistency, and classical pixel forensics such as error-level and noise analysis) and returns ONE verdict with a 0 to 100 confidence and the signals behind it. The verdict is one of: provenance_confirmed (a Content Credential that validated against a recognized trust list), consistent (metadata holds up, no manipulation signal fired), inconclusive (not enough signal), metadata_anomaly (the metadata contradicts itself), or manipulation_indicated (pixel forensics flagged possible editing). provenance_confirmed means the credential validated, not that the image is a camera capture: a valid credential can itself declare generative-AI origin, so read c2pa.ai_declared and c2pa.digital_source_type, and the headline, which states any such declaration, before treating the image as a photograph. Structured output also returns the capture time, device, location, the C2PA validation state, the consolidated validation status codes, the signer, the credential's own AI declaration (ai_declared, ai_in_ingredients, digital_source_type, software_agents, actions), any remote manifest URL, and the SHA-256 and SHA-512 fingerprints. Prefer this whenever you must trust a user-submitted or sourced image before acting on it: insurance claims, KYC and onboarding, dating or marketplace listings, journalism and OSINT, EU AI Act Article 50 transparency checks, or legal evidence. Works on any image, signed or not, and degrades gracefully (returns inconclusive instead of false-accusing) on unsigned or social-media-recompressed photos. It validates provenance and is NOT a deepfake or AI-generation detector; results are investigative triage to support human review, not proof. Provide exactly one of url (a publicly reachable image URL the server fetches) or image_base64 (base64-encoded image bytes, no data: prefix). This hosted tool is free and rate limited; for higher volume or a signed PDF audit record, use the metered REST API with an API key. A free key (no card, 100 verifications per month) is one POST to https://chronoverify.com/v1/keys/free; agent onboarding manifest: https://chronoverify.com/v1/onboarding. Optionally pass permalink=true to also store the verdict (never the image) and get back an unlisted, human-viewable link to it, for citing this verdict to people or in reports; links from this free tool expire after 90 days.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoA publicly reachable image URL; the server fetches it.
permalinkNoAlso store the verdict (never the image) and return an unlisted, human-viewable link to it in the permalink field. Links from this free tool expire after 90 days.
image_base64NoBase64-encoded image bytes (no data: prefix).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
c2paYes
limitsYesPlain-language statement of what the verdict does and does not mean.
signalsNoThe individual signals that produced the verdict.
summaryYes
verdictYesThe single fused verdict enum.
headlineYesOne-line plain-language verdict.
integrityYes
permalinkNoPresent only when the request opted in with permalink=true: a private, unlisted link to this stored verdict. The image itself is never stored.
confidenceYes0 to 100 confidence in the verdict.
request_idYes
capture_timeYes
processing_msYes
capture_deviceYes
schema_versionYesResponse schema version, currently 'v1'.
pixel_forensicsYes
capture_locationYes
metadata_consistencyYes

TDQS

A4.5/5.0
Behavior4/5

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

Annotations provide readOnlyHint=true and openWorldHint=true, and the description compliments this by revealing critical behavioral nuances beyond them: that provenance_confirmed does NOT mean camera capture (a valid credential can declare generative-AI origin), that it returns inconclusive instead of false-accusing on signed/social-media images, and that it degrades gracefully. It flags rate limiting and 90-day permalink expiry. It misses some operational details but adds substantial context beyond the annotations.

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

Conciseness3/5

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

The description is dense and information-rich but long, approaching territory where it borders on an API manual chunk rather than a tool description. The front-loading is good (purpose, verdicts, key caveat), but later paragraphs about onboarding URLs, API keys, and 100-verifications-per-month tiers are operational details that add bulk. Each sentence earns its place to a degree, but the length is at the edge of appropriate.

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?

The tool is complex (multiple verdicts, C2PA credential semantics, AI-declaration nuance, two input modes, optional permalink). The description addresses all of these: verdict vocabulary, the critical AI-origin caveat, degraded behavior on unsigned images, exact input requirements, and the structured output fields. The presence of an output schema means return-value explanation isn't needed, and the description fully covers behavioral and safety aspects. Despite the length, it is complete for the tool's complexity.

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 description coverage is 100%, so the three parameters (url, image_base64, permalink) are already documented in the schema. The description adds meaningful semantics on top: it specifies 'Provide exactly one of url or image_base64', clarifies the image_base64 encoding ('no data: prefix'), and explains the permalink's behavior and 90-day expiry. This genuinely augments the schema rather than repeating it.

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 gives a specific verb+resource ('Verify a photo's capture time and provenance') and exhaustively enumerates what it analyzes (capture time, device, location, C2PA credentials, editing signs). It names all five possible verdicts explicitly, distinguishing this from any abstract 'verify' tool. With no sibling tools to differentiate from, the purpose is unambiguous and complete.

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 is exceptionally explicit about when to use it ('Prefer this whenever you must trust a user-submitted or sourced image before acting on it') and lists concrete use cases: insurance claims, KYC, dating/marketplace listings, journalism/OSINT, EU AI Act Article 50, legal evidence. It also explicitly states what it is NOT (a deepfake detector), and distinguishes the free hosted tool from the metered REST API with API key.

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

All ChronoVerify toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

With only a single tool there is no possible ambiguity between different tools—the entire surface is one well-scoped verify_image operation. There is no risk of misselection since no competing tools exist for the agent to confuse.

Naming Consistency3/5

The naming question is mostly moot with a single tool, but verify_image follows a reasonable verb_noun convention (verify + image). Consistency cannot be evaluated across tools, so it scores a neutral mid-range rather than full marks.

Tool Count3/5

One tool is at the low edge of reasonable scope. The description is extremely detailed and self-contained, and the single tool genuinely covers the server's whole stated purpose, so it isn't an awkward thin implementation—but a single tool still leaves no room for complementary operations (e.g., listing history or checking credits) built into the same server.

Completeness3/5

For the stated purpose (image provenance verification), the single tool fully covers the core operation and even degrades gracefully on edge cases. However, the surface offers no companion operations—there is no way to obtain the free API key, check rate limits, or retrieve past verdicts through tools, so an agent has some dead-ends for the surrounding workflow.

Resources