🔗 DISCOVER RELATED DOCUMENTS across collections. Input any package ID to find connected documents like bill status, different bill versions, congressional record mentions, and bill history. Tested: BILLS-119hr445ih links to BILLSTATUS (status tracking), BILLS (other versions), HOB (bill history)...
AI agents call related to retrieve information from Gov info api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search and retrieval operation that queries existing government data to return related documents. There are no side effects, no data modification, no code execution, and no destructive actions. The tool supports legislative research by linking documents together, which is purely informational.
From the tool's definition The tool description explicitly states it "DISCOVER[s] RELATED DOCUMENTS" and "find[s] connected documents" in response to a package ID input.
Attacks that exploit this kind of access
🔗 DISCOVER RELATED DOCUMENTS across collections. Input any package ID to find connected documents like bill status, different bill versions, congressional record mentions, and bill history. Tested: BILLS-119hr445ih links to BILLSTATUS (status tracking), BILLS (other versions), HOB (bill history), and CREC (Congressional Record references). Essential for comprehensive bill tracking and legislative research. It is categorised as a Read tool in the Gov info api MCP Server, which means it retrieves data without modifying state.
Register the Gov info api MCP server in PolicyLayer and add a rule for related: 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 Gov info api. Nothing to install.
related 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 related 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 related. 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.
related is provided by the Gov info api MCP server (n00dlefr34k/gov-info-api-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 →