EU AI Act Credit-Scoring Conformity Pack — OpenChainGraph compute node (model_governance). Regulatory deadline: 2026-08-02 (EU AI Act Annex III Part 5(b) — credit-scoring high-risk obligations fully apply August 2, 2026). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 ar...
AI agents call assess_ai_act_conformity 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.
This is a deterministic, read-only compliance assessment tool that queries and validates credit-scoring configurations against regulatory standards. It produces an artifact (execution_hash for provenance) but does not create reversible modifications to data, execute arbitrary code/commands, delete data, or move money. The tool operates in-browser with zero egress, confirming no external state changes.
From the tool's definition Tool description explicitly states: 'Runs deterministically in-browser; zero PII, zero egress' and 'Read-only, no auth, zero PII' per server description.
Attacks that exploit this kind of access
EU AI Act Credit-Scoring Conformity Pack — OpenChainGraph compute node (model_governance). Regulatory deadline: 2026-08-02 (EU AI Act Annex III Part 5(b) — credit-scoring high-risk obligations fully apply August 2, 2026). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Output feeds: ml-01-isolation-forest, ptg-01-ap2-prompt-template-generator. Open at: https://ainumbers.co/chaingraph/art-05-eu-ai-act-credit-scoring-conformity.html. It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
assess_ai_act_conformity 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 assess_ai_act_conformity: 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.
assess_ai_act_conformity 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 assess_ai_act_conformity 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 assess_ai_act_conformity. 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.
assess_ai_act_conformity 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 →