Federal counterparty due-diligence dossier on one name, in a single call: SAM registration + SAM exclusions (debarment) + OFAC SDN sanctions + GLEIF LEI + USAspending federal awards + FARA foreign-agent registration. Returns headline riskFlags (federally_debarred, sanctions_high_confidence_match,...
AI agents call gov.counterparty 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 performs due-diligence queries across public federal databases. It reads and aggregates pre-existing government records to produce a compliance report. There are no side effects, irreversible actions, code execution, or financial transactions.
From the tool's definition Tool description states it retrieves and aggregates existing federal records: 'SAM registration + SAM exclusions + OFAC SDN sanctions + GLEIF LEI + USAspending federal awards + FARA foreign-agent registration.' Returns 'headline riskFlags' and 'summary' —…
Attacks that exploit this kind of access
Federal counterparty due-diligence dossier on one name, in a single call: SAM registration + SAM exclusions (debarment) + OFAC SDN sanctions + GLEIF LEI + USAspending federal awards + FARA foreign-agent registration. Returns headline riskFlags (federally_debarred, sanctions_high_confidence_match, registered_foreign_agent), a cleared boolean (debarment+sanctions only — FARA is context), a summary, and per-source found/error blocks. Free, public-domain. The federal counterpart to business.entity-screen. 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.counterparty: 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.counterparty 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.counterparty 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.counterparty. 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.counterparty 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 →