ChronoVerify

ChronoVerify integrations

Wire ChronoVerify into your agent, framework, or workflow. One verification primitive, every runtime.

ChronoVerify is the provenance primitive your agent calls before trusting an image: it validates C2PA Content Credentials, reads EXIF and XMP, runs pixel forensics, and returns one verdict with a confidence and a signed audit record. Pick your stack below.

When your agent should call ChronoVerify

Call it before you trust or act on any user-submitted or sourced image. Strong triggers:

Branch on the verdict and confidence it returns; treat anything below your bar as needing human review.

What comes back

One JSON object, the same in the browser and the API. The verdict is one of provenance_confirmed, consistent, inconclusive, metadata_anomaly, or manipulation_indicated.

{
  "schema_version": "v1",
  "verdict": "consistent",
  "confidence": 61,
  "headline": "Metadata is internally consistent. No manipulation signals fired.",
  "capture_time": {
    "value": "2026-05-18T14:32:10",
    "source": "exif",
    "consistent": null
  },
  "capture_device": {
    "make": "Canon",
    "model": "EOS R6",
    "software": "Firmware 1.8.1"
  },
  "c2pa": {
    "present": false,
    "validated": null,
    "validation_state": null,
    "signer": null
  },
  "integrity": {
    "sha256": "1313339a...",
    "sha512": "93a81e4a...",
    "format": "JPEG"
  }
}

Full field reference, including the C2PA validation state and signer, is on the method and API page and in /openapi.json.

What it does and does not tell you

ChronoVerify validates provenance and metadata and flags possible editing for human review. It is not a deepfake or AI-generation detector, and a verdict is investigative triage, not proof. A clean result means a file's saved data is internally consistent, not that the scene it shows is real. Never use a verdict as the sole basis for an automated decision about a person.

Common questions

Which integration should I use?

If you use Claude Desktop, Claude Code, Cursor, or VS Code, install the MCP server: it is one click and your assistant gets verify_image and get_signed_report. If you build an agent on the OpenAI or Anthropic API, use the function-calling definition. If you use LangChain, LlamaIndex, or CrewAI, point its MCP adapter at the published server. Everything else is one REST call.

Do I need an API key?

Not to try it. Every path works against the free, rate-limited public endpoint. Add CHRONOVERIFY_API_KEY (a cv_live_... key) for metered, higher-volume use.

Is ChronoVerify a deepfake detector?

No. It is provenance-first and returns investigative triage, not an AI-or-real score. See the method and limits.

See it on a real photo first.

Try the free verifier