Agentic AI Risk & GPAI Governance Classifier — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Consumes upstream artifacts from: art-64-ai-act-highrisk-fit-diagnostic. Outpu...
AI agents call classify_agentic_ai_risk 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 performs a deterministic classification/governance assessment of agentic AI risk. It consumes upstream artifacts and produces output artifacts (an AP2 artifact with execution_hash), but this is a read/analyze operation with no writes, deletions, or financial transactions. The server is explicitly described as read-only with zero PII and zero egress, confirming no side effects.
From the tool's definition Runs deterministically in-browser; zero PII, zero egress. Read-only, no auth, zero PII (server description). 'Classifier' and 'Diagnostic' language implies analysis/classification without side effects.
Attacks that exploit this kind of access
Agentic AI Risk & GPAI Governance Classifier — OpenChainGraph compute node (model_governance). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Consumes upstream artifacts from: art-64-ai-act-highrisk-fit-diagnostic. Output feeds: art-04-agent-identity-attestation-checker, art-33-mcp-server-self-attestation-pack, art-62-ap2-payment-receipt-verifier. Open at: https://ainumbers.co/chaingraph/art-67-agentic-ai-risk-classifier.html. It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
classify_agentic_ai_risk 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 classify_agentic_ai_risk: 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.
classify_agentic_ai_risk 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 classify_agentic_ai_risk 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 classify_agentic_ai_risk. 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.
classify_agentic_ai_risk 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 →