Visa Trusted Agent Protocol (TAP) Signature Inspector — OpenChainGraph compute node (compliance_control). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Consumes upstream artifacts from: art-22-agentic-payments-protocol-...
AI agents call inspect_visa_trusted_agent_protocol to retrieve information from Ainumbers Mcp Apps without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
compute | string | — | Compute mode (v0.4 Compute Binding). "auto" (default) = server for gpu:false nodes with registered kernels; "server" = force server-side; "browser" = always ret |
parent_hashes | array | — | execution_hash values from upstream ChainGraph AP2 artifacts to chain from (sets chain.parent_hashes in the export). |
parent_tool_ids | array | — | tool_id values matching parent_hashes, in the same order. |
policy_parameters | object | — | Input parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is "auto" or "serv |
Parameters from the server's own tool schema.
The tool is a protocol signature inspector that runs deterministically with no egress and no PII. It reads/inspects Visa TAP signatures and produces an artifact hash for provenance. Despite touching payment-adjacent protocols, it is explicitly described as read-only with zero external effects, placing it firmly in the Read category. The artifact export is a local output (hash/metadata), not a financial transaction.
From the tool's definition Runs deterministically in-browser; zero PII, zero egress. Read-only, no auth, zero PII. 'Signature Inspector' — inspection/read operation. Exports an AP2 artifact with execution_hash for chain provenance.
Attacks that exploit this kind of access
Visa Trusted Agent Protocol (TAP) Signature Inspector — OpenChainGraph compute node (compliance_control). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Consumes upstream artifacts from: art-22-agentic-payments-protocol-comparator, art-16-google-ap2-mandate-builder. Output feeds: art-24-mastercard-agentic-token-builder, art-18-mcp-developer-readiness-scorecard, ptg-01-ap2-prompt-template-generator. Open at: https://ainumbers.co/chaingraph/art-23-visa-trusted-agent-protocol-inspector.html. It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
inspect_visa_trusted_agent_protocol accepts 4 parameters: compute, parent_hashes, parent_tool_ids, policy_parameters. The full parameter table on this page comes from the server's own tool schema.
Register the Ainumbers Mcp Apps MCP server in PolicyLayer and add a rule for inspect_visa_trusted_agent_protocol: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ainumbers Mcp Apps. Nothing to install.
inspect_visa_trusted_agent_protocol is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the inspect_visa_trusted_agent_protocol rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for inspect_visa_trusted_agent_protocol. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
inspect_visa_trusted_agent_protocol is provided by the Ainumbers Mcp Apps MCP server (postoaklabs/ainumbers-mcp-apps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →