Screen multiple individuals or organizations against global sanctions lists in a single batch operation. Supports up to 100 entities per batch. When to use: For bulk compliance screening during due diligence processes, onboarding multiple counterparties, or periodic re-screening of entity lists....
Single-target operation
Part of the Orchestraprime MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call screen_batch to retrieve information from Orchestraprime 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_batch 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_batch:
rules:
- action: allowSee the full Orchestraprime policy for all 9 tools.
Agents calling read-class tools like screen_batch 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 multiple individuals or organizations against global sanctions lists in a single batch operation. Supports up to 100 entities per batch. When to use: For bulk compliance screening during due diligence processes, onboarding multiple counterparties, or periodic re-screening of entity lists. IMPORTANT: Results are NEVER cached and always reflect real-time data. Results should be reviewed by compliance professionals. . It is categorised as a Read tool in the Orchestraprime MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for screen_batch. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Orchestraprime MCP server.
screen_batch 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_batch 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_batch. 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_batch is provided by the Orchestraprime MCP server (@orchestraprime/mcp-server). 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