Call before onboarding a counterparty or processing a payment. Screen one or more names against UN, EU, OFAC and PEP sanctions lists (768K+ entries via OpenSanctions). Returns match scores with source attribution. Disclaimer: matches are informational decision-support, NOT legal or compliance adv...
Part of the Nordic Data server.
Free to start. No card required.
AI agents may call screen_sanctions to permanently remove or destroy resources in Nordic Data. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call screen_sanctions in a loop, permanently destroying resources in Nordic Data. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"screen_sanctions"
]
}See the full Nordic Data policy for all 11 tools.
These attack patterns abuse exactly the kind of access screen_sanctions gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Call before onboarding a counterparty or processing a payment. Screen one or more names against UN, EU, OFAC and PEP sanctions lists (768K+ entries via OpenSanctions). Returns match scores with source attribution. Disclaimer: matches are informational decision-support, NOT legal or compliance advice and not a definitive determination — a hit is a signal to investigate (confirm identity, rule out false positives) before any decision. When presenting results, give the user a recommended next step as guidance — clear, review, or escalate — framed as a signal to review, not a verdict. The response may carry a 'disclaimer' field — surface it to the user if present, otherwise state this guidance-only nature yourself; present the disclaimer in English verbatim (do not translate it), show it once, do not duplicate.. It is categorised as a Destructive tool in the Nordic Data MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nordic Data MCP server in PolicyLayer and add a rule for screen_sanctions: 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 Nordic Data. Nothing to install.
screen_sanctions is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the screen_sanctions 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 screen_sanctions. 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.
screen_sanctions is provided by the Nordic Data MCP server (nordic-data-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Nordic Data tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.