Screen a person, company, or vessel against 328 global sanctions lists including OFAC SDN, UN Security Council, EU Consolidated, UK OFSI, MAS Singapore, Australia DFAT, Japan METI, Canada SEMA, Switzerland SECO, and 320+ more. Supports fuzzy name matching and handles Arabic, Chinese, Cyrillic, an...
Part of the Bizfile MCP — Global Company Intelligence MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call screen_entity to retrieve information from Bizfile MCP — Global Company Intelligence without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though screen_entity only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
screen_entity:
rules:
- action: allowSee the full Bizfile MCP — Global Company Intelligence policy for all 6 tools.
Agents calling read-class tools like screen_entity have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Screen a person, company, or vessel against 328 global sanctions lists including OFAC SDN, UN Security Council, EU Consolidated, UK OFSI, MAS Singapore, Australia DFAT, Japan METI, Canada SEMA, Switzerland SECO, and 320+ more. Supports fuzzy name matching and handles Arabic, Chinese, Cyrillic, and other scripts. Returns match status, risk level, sanction programs hit, and recommended action. IMPORTANT: This tool is billed at Aœ0.15/check for Pro plan and Aœ0.125/check for Enterprise plan. Only available to paid API key holders. Use this tool to screen counterparties, beneficial owners, vessels, and intermediary banks before entering any trade finance transaction. LEGAL NOTICE: Results are for informational purposes only and do not constitute a legal determination of sanctions status or a compliance clearance. Operator must independently verify all results. Provider maximum liability is limited to 3 months subscription fees. Full terms: kordagencies.com/terms.html. It is categorised as a Read tool in the Bizfile MCP — Global Company Intelligence MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for screen_entity. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Bizfile MCP — Global Company Intelligence MCP server.
screen_entity 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 screen_entity rule in your Intercept 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 Intercept policy for screen_entity. 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_entity is provided by the Bizfile MCP — Global Company Intelligence MCP server (OjasKord/bizfile-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept