W-G convergence terminal. Merkle integrity over the AI-governance decision set (cry-04) -> one Merkle-root audit receipt (cry-05) -> regulator/notified-body-framed cover memo (ptg-01). Other Wave-15 chains can feed in.
verify_merkle_batch{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "verify_merkle_batch",
"arguments": {}
},
"id": 1
}
aggregate_execution_receipts{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "aggregate_execution_receipts",
"arguments": {}
},
"id": 1
}
compose_ap2_prompt{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "compose_ap2_prompt",
"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 hand the pack to the regulator, do the execution receipts in the evidence batch still verify against the Merkle root we committed?
Run the AINumbers MCP tool `run_chain` with {"chain":"ai-governance-audit-pack"} and read `cry-04-merkle-batch-verifier.batch_integrity`.
Re-run with `inputs` for `cry-04-merkle-batch-verifier`, reusing the values that result echoed, with `proof_entries` changed so one entry whose leaf equals the declared root, carrying an empty inclusion proof. 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/ai-governance-audit-pack.html