AMLA Transaction-Typology Risk Scorer — OpenChainGraph compute node (risk_control). Regulatory deadline: 2027-07-01 (EU AMLR full application July 2027; AMLA full operations 2028). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain prov...
AI agents call score_aml_typologies 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.
Despite the fintech context and AML/regulatory purpose, the tool's primary function is to compute and return a risk score based on transaction data. The phrase 'deterministically in-browser' and 'zero egress' confirms it performs read-only analysis without side effects. It feeds outputs to downstream tools but does not itself execute transactions, modify records, or commit financial obligations.
From the tool's definition Tool name and description indicate it 'Runs deterministically in-browser; zero PII, zero egress' and 'Exports an AP2 artifact' — it scores and analyzes transaction typologies for AML compliance but does not create, modify, delete, execute code, or move money.
Attacks that exploit this kind of access
AMLA Transaction-Typology Risk Scorer — OpenChainGraph compute node (risk_control). Regulatory deadline: 2027-07-01 (EU AMLR full application July 2027; AMLA full operations 2028). Runs deterministically in-browser; zero PII, zero egress. Exports an AP2 artifact with execution_hash for chain provenance. Output feeds: cry-01-zk-compliance-proof-generator, art-11-vop-batch-match-rate-analyser, ptg-01-ap2-prompt-template-generator, mms-03-app-fraud-graph, ml-01-isolation-forest. Open at: https://ainumbers.co/chaingraph/art-10-amla-transaction-typology-risk-scorer.html. It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
score_aml_typologies 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 score_aml_typologies: 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.
score_aml_typologies 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 score_aml_typologies 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 score_aml_typologies. 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.
score_aml_typologies 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 →