chronoverify-mcp
This server lets you verify the authenticity and provenance of images using forensic analysis, and generate signed audit reports.
verify_image – Analyzes a photo's capture time, device, and editing history by examining:
C2PA Content Credentials – checks for a trusted, validated digital provenance chain
EXIF/XMP metadata – inspects consistency, capture time, device make/model, software, and location
Pixel-level forensics – error-level analysis, double-compression detection, and copy-move detection
Accepts input as a public URL, absolute local file path, or base64-encoded image. Returns a verdict with a confidence score (0–100) and human-readable summary. Possible verdicts:
provenance_confirmed– trusted C2PA credential validatedconsistent– metadata holds up, no manipulation signalsinconclusive– insufficient signalmetadata_anomaly– metadata contradicts itselfmanipulation_indicated– pixel forensics flagged possible editing
Optionally generates a shareable, unlisted permalink to the result (permalink: true).
get_signed_report – Creates a signed PDF audit report (Ed25519 signature) for an image, suitable for chain-of-custody, compliance, legal evidence, or newsroom audit trails. Requires an API key; accepts a file path or base64 input.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@chronoverify-mcp Verify the provenance of /Users/me/Downloads/photo.jpg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
chronoverify-mcp
An MCP server for ChronoVerify. It gives any MCP-compatible AI agent (Claude Desktop, Cursor, Cline, VS Code, and others) the tools to check a photo's capture time and provenance: C2PA Content Credentials, EXIF and XMP metadata, and classical pixel forensics, fused into one verdict (provenance_confirmed, consistent, inconclusive, metadata_anomaly, or manipulation_indicated) with a 0 to 100 confidence.
Provenance-first, not a deepfake or AI-generation detector. Results are investigative triage to support human review, not proof.
ChronoVerify is a C2PA Conformant Validator, listed on the C2PA Conforming Products List (record 019f8a20-6452-7a43-b11b-59d0b0e4a84a; validation of JPEG, PNG, WebP, and AVIF). Details: https://chronoverify.com/compliance#conformance
Source and issues: github.com/beeswaxpat/chronoverify-mcp
Listed on Smithery: https://smithery.ai/servers/beeswaxpat/chronoverify-mcp
Get an API key (the first 100 verifications each month are included): https://chronoverify.com/pricing . Without a key,
verify_imageuses the free, rate-limited public path. A signed report requires a key.
Install
Add it to your MCP client config. For Claude Desktop (claude_desktop_config.json) or any MCP client:
{
"mcpServers": {
"chronoverify": {
"command": "npx",
"args": ["-y", "chronoverify-mcp"],
"env": { "CHRONOVERIFY_API_KEY": "cv_live_..." }
}
}
}Omit the env block to use the free public path (verification only; signed reports always need a key).
Related MCP server: vision-mcp
Tools
verify_image
Verify a photo's capture time and provenance. Takes exactly one of:
url: a publicly reachable image URL (the server fetches it),file_path: an absolute path to a local image, orimage_base64: base64-encoded image bytes.
Optionally set permalink: true to also store the verdict (never the image) and get back an unlisted, shareable link to it in the permalink field, for citing the result to people or in reports. Keyless links expire after 90 days; links minted with an API key do not expire.
It returns a human-readable summary and a typed structured object so an agent can branch on the result without parsing prose:
{
"schema_version": "v1",
"verdict": "consistent",
"confidence": 58,
"headline": "Metadata is internally consistent. No manipulation signals fired.",
"summary": "...",
"capture_time": { "value": "2026-03-14T09:21:30", "source": "exif", "consistent": null },
"capture_device": { "make": "Canon", "model": "EOS R6", "software": "Firmware 1.8.1" },
"capture_location": { "present": false, "place": null },
"c2pa": {
"present": false,
"validated": null,
"validation_state": null,
"signature_valid": null,
"trust_list_match": null,
"signer": null
},
"integrity": {
"sha256": "1313339a...",
"sha512": "93a81e4a...",
"format": "JPEG",
"width": 1200,
"height": 800,
"c2pa_validator_enabled": true
},
"permalink": null,
"limits": "ChronoVerify returns investigative triage, not proof.",
"source": "ChronoVerify (https://chronoverify.com)"
}The verdict enum:
provenance_confirmed: a trusted C2PA Content Credential validated against the official trust list.consistent: metadata holds up and no manipulation signal fired (consistent with an unedited capture, not proof).inconclusive: not enough signal to decide.metadata_anomaly: the metadata contradicts itself.manipulation_indicated: pixel forensics flagged possible editing for human review.
get_signed_report
Generate a signed PDF audit report for one image: the chain-of-custody / compliance record (for example an EU AI Act Article 50 transparency record, an insurance or legal evidence file, or a newsroom audit trail). Takes one of file_path or image_base64 (this endpoint does not fetch URLs) and an optional out_path. Writes the PDF and returns the path. Requires CHRONOVERIFY_API_KEY; metered as a premium report unit. The report carries an Ed25519 signature you can verify against the public key at https://chronoverify.com/v1/key.
Example prompts
"Verify the provenance of /Users/me/Downloads/photo.jpg"
"When was the photo at this URL taken, and has it been edited? https://example.com/photo.jpg"
"Validate the C2PA Content Credentials on this image and tell me the signer."
"Verify this photo and give me a shareable link to the verdict."
"Generate a signed provenance report for ./evidence/claim-001.jpg and save it to ./reports/"
License
MIT
Available Tools
1 toolverify_imageARead-only
Verify whether a photo is authentic: when it was captured, on what device, and whether it shows signs of editing or AI generation. Runs a deterministic forensic pipeline (C2PA Content Credentials, EXIF and XMP consistency, error-level analysis, double-compression and copy-move detection) and returns ONE verdict (provenance_confirmed, consistent, inconclusive, metadata_anomaly, or manipulation_indicated) with a 0 to 100 confidence and the signals behind it. 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, 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. Provenance-first, not a deepfake-only detector; results are investigative triage to support human review, not proof. Provide exactly one of url, file_path, or image_base64.
Inputs: url, file_path, image_base64.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined and distinct.
The single tool name 'verify_image' follows a clear verb_noun pattern, which is consistent and predictable.
The server has only one tool for image verification, which feels thin for the scope. While the tool is comprehensive, breaking it into separate forensic steps could improve modularity.
The tool covers a wide range of forensic analyses (C2PA, EXIF, compression, copy-move) and returns a verdict with confidence and signals. However, it does not provide separate tools for granular access to specific analyses, which may be a minor gap.
Maintenance
Related MCP Connectors
Verify photos are real camera captures, not AI: C2PA and RAW+JPEG forensics. OAuth or API key.
Sign media with C2PA Content Credentials and verify its declared origin.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Provenance and metadata tools for AI agents. Paid tools use x402 (USDC) at /mcp/<tool>.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables reading and verifying C2PA Content Credentials from images and videos through both embedded manifests and invisible watermarks. Supports direct filesystem access, URL checking, and provides structured provenance data including creator identity, AI generation info, and content authenticity.2MIT
- AlicenseAqualityCmaintenanceGive MCP-compatible AI agents image analysis, metadata inspection, cropping, OCR, and image comparison through any OpenAI-compatible vision model.6MIT
- FlicenseNot gradedqualityCmaintenanceEnables MCP clients to analyze, inspect, and manipulate images and videos with deterministic FFmpeg/sharp tools and pluggable AI providers, returning timestamped, evidence-backed results that can be independently re-verified.1-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to verify claims against evidence through MCP tools, returning approved, rejected, or needs_review verdicts with replayable receipts.MIT