Search currently-active FARA (Foreign Agents Registration Act) registrants by name. Returns whether the entity is a registered foreign agent (isRegisteredForeignAgent), a KYB-safe bestMatch (null below medium confidence — no false positives), and scored candidates with registration number, date, ...
AI agents call gov.foreign-agents 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 tool retrieves and queries public FARA registration data from a government database. It has no side effects—it only reads and returns information. The data source is explicitly noted as a free, public DOJ FARA eFile database. There is no capability to modify records, execute code, delete data, or trigger financial transactions.
From the tool's definition Tool performs search and returns query results: 'Search currently-active FARA registrants by name. Returns whether the entity is a registered foreign agent...scored candidates with registration number, date, and city/state.' No modification, deletion, or…
Attacks that exploit this kind of access
Search currently-active FARA (Foreign Agents Registration Act) registrants by name. Returns whether the entity is a registered foreign agent (isRegisteredForeignAgent), a KYB-safe bestMatch (null below medium confidence — no false positives), and scored candidates with registration number, date, and city/state. FARA registration is a US disclosure status (acting for a foreign principal), not wrongdoing. DOJ FARA eFile, free and keyless. 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 gov.foreign-agents: 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.
gov.foreign-agents 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 gov.foreign-agents 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 gov.foreign-agents. 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.
gov.foreign-agents 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 →