Generate an ISCC content fingerprint, declare AI-training rights via TDMRep, validate any on-chain royalty split, produce a TASL attribution string, and certify the result as a tokenization-ready license VC. The royalty-split step is optional: pass empty input if no on-chain split applies and the workflow continues to certification.
generate_iscc_code{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "generate_iscc_code",
"arguments": {}
},
"id": 1
}
build_tdm_reservation{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "build_tdm_reservation",
"arguments": {}
},
"id": 1
}
validate_royalty_split{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "validate_royalty_split",
"arguments": {}
},
"id": 1
}
generate_attribution_string{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "generate_attribution_string",
"arguments": {}
},
"id": 1
}
certify_license_election{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "certify_license_election",
"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: We are preparing the catalog asset for tokenization. Which royalty split finding blocks a clean prep pack?
Run the AINumbers MCP tool `run_chain` with {"chain":"tokenization-prep"} and read `art-208-royalty-split-validator.valid`.
Re-run with `inputs` for `art-208-royalty-split-validator`, reusing the values that result echoed, with `cap_bps` changed so cap_bps set to 4000, keeping the two 5000 bps entries. 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/tokenization-prep.html