Look up US 501(c) nonprofits and screen each against the OFAC sanctions list in one call: registry record (EIN, name, location, NTEE) + per-org sanctions block (flagged, match count, SDN matches with confidence). Grant-making due diligence and donation compliance.
AI agents call nonprofit.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 fundamentally a Read operation—it queries nonprofit databases and OFAC sanctions lists to retrieve compliance information. The tool has no side effects on the data it accesses.
From the tool's definition The tool description explicitly states 'Look up US 501(c) nonprofits' (read operation) and 'screen...against the OFAC sanctions list' (query/compliance check).
Attacks that exploit this kind of access
Look up US 501(c) nonprofits and screen each against the OFAC sanctions list in one call: registry record (EIN, name, location, NTEE) + per-org sanctions block (flagged, match count, SDN matches with confidence). Grant-making due diligence and donation compliance. 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 nonprofit.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.
nonprofit.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 nonprofit.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 nonprofit.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.
nonprofit.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 →