Run a structural C2PA provenance check on an identity-verification capture, then bind the same verdict into a hash-chained IDV/KYC session receipt that binds capture-chain digest, injection, liveness, document, and device verdicts into one tamper-evident record. Every field is labeled asserted: the chain attests the session record as declared, never detection quality or subject genuineness. Zero PII by construction, client-side only.
check_camera_provenance{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "check_camera_provenance",
"arguments": {}
},
"id": 1
}
build_idv_session_receipt{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "build_idv_session_receipt",
"arguments": {}
},
"id": 1
}
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.
Question: Before we accept this selfie capture for onboarding, does its C2PA manifest assert a live camera shot or AI-generated media?
Run the AINumbers MCP tool `run_chain` with {"chain":"idv-session-evidence"} and read `art-361-camera-provenance-check.provenance_label`.
Re-run with `inputs` for `art-361-camera-provenance-check`, reusing the values that result echoed, with `assertions` changed so the first action declares trainedAlgorithmicMedia. Compare the same field.
Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`.
Ledger, for a human re-check: https://ledger.ainumbers.co/
PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads.
Chain page: https://ainumbers.co/chaingraph/chains/idv-session-evidence.html