ART-21 · Node 3 of 3 · Agentic Checkout Chain · OpenChainGraph

Agent-Traffic Acceptance Policy Builder

Define which AI agents your API or platform will accept, at what verification level, under what velocity and value caps, and on which payment rails. Outputs a §4 hash-anchored OpenChainGraph Policy Mandate the agent can read to confirm acceptance terms before initiating a transaction.

§4 OpenChainGraph · Agent Guardrail Client-Side Zero PII AP2 / ACP · Policy Mandate ART-21 · v1.0.0
🔒 All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Accepted Agent Types
Select which agent types are permitted to transact with your API or service
Identity Verification Level
Minimum identity check required before accepting an agent request
Velocity Caps & Limits
Per agent session / credential
Per agent identity (or IP if anonymous)
Aggregate per agent identity per day
Payment Rails & Refund Posture
Blocking Rules
Policy Summary
ParameterValue
Guardrail Assessment
    Agent-Readable Instructions Block

    Paste this into your API documentation or serve it as a /agent-policy endpoint so AI agents can read acceptance terms before initiating requests.

    Related OpenChainGraph Nodes
    ART-15 Agentic Mandate Sandbox — test your policy mandate against simulated agent requests
    ART-19 Protocol Selector — pick the right agentic checkout protocol for your merchant profile
    ART-20 ACP/UCP Conformance Auditor — validate your product/checkout payload schema

    Ask your agent

    Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.

    Run the AINumbers MCP tool `build_agent_traffic_policy`. Task: Build a policy mandate governing accepted AI agent types, identity verification level, velocity and value caps, payment rails, refund posture, retry policy, and blocking rules.
Call it with arguments: {"policy_parameters":{"agent_types":["openai"],"verification_level":"ap2_vdc","max_tx_per_min":60,"max_tx_per_day":5000,"max_single_val_usd":100,"max_daily_val_usd":1000,"rails":["acp","x402"],"refund_posture":"standard","retry_policy":"retry_1x","block_rules":["block_burst","block_anon_high"]}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-21-agent-traffic-acceptance-policy-builder.html#p=v1.H4sIAAAAAAAA_wESAe3-eyJhZ2VudF90eXBlcyI6WyJvcGVuYWkiXSwidmVyaWZpY2F0aW9uX2xldmVsIjoiYXAyX3ZkYyIsIm1heF90eF9wZXJfbWluIjo2MCwibWF4X3R4X3Blcl9kYXkiOjUwMDAsIm1heF9zaW5nbGVfdmFsX3VzZCI6MTAwLCJtYXhfZGFpbHlfdmFsX3VzZCI6MTAwMCwicmFpbHMiOlsiYWNwIiwieDQwMiJdLCJyZWZ1bmRfcG9zdHVyZSI6InN0YW5kYXJkIiwicmV0cnlfcG9saWN5IjoicmV0cnlfMXgiLCJibG9ja19ydWxlcyI6WyJibG9ja19idXJzdCIsImJsb2NrX2Fub25faGlnaCJdfUqFMysSAQAA