KYC in one call: look up a business in a US state registry (NY/CO/CT) AND screen it + its registered agent against OFAC sanctions. Returns matched entities each with a sanctions screen (confidence + flagged). Counterparty due-diligence, AML. Probabilistic name match.
AI agents call business.entity-screen to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a KYC/AML lookup and screening tool that retrieves and cross-references data from public registries and OFAC sanctions lists. While the information it returns informs compliance decisions, the tool itself performs read-only queries without side effects. There is no creation, modification, deletion of records, code execution, or financial transaction.
From the tool's definition 'look up a business in a US state registry' and 'screen it...against OFAC sanctions' — both retrieval and screening operations with no data modification.
Attacks that exploit this kind of access
KYC in one call: look up a business in a US state registry (NY/CO/CT) AND screen it + its registered agent against OFAC sanctions. Returns matched entities each with a sanctions screen (confidence + flagged). Counterparty due-diligence, AML. Probabilistic name match. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for business.entity-screen: 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 Mcp. Nothing to install.
business.entity-screen 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 business.entity-screen 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 business.entity-screen. 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.
business.entity-screen is provided by the MCP server (@2sio/mcp). 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 →