This can be used to visualize government spending that pertains to a specific recipient.
AI agents call recipient to retrieve information from Usaspending without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and visualizes spending data for a specified recipient without creating, modifying, deleting, or executing any operations. It is purely informational access to public government spending records. No side effects or irreversible actions are possible.
From the tool's definition Tool description states it can be 'used to visualize government spending that pertains to a specific recipient' - this is a query/retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
This can be used to visualize government spending that pertains to a specific recipient. It is categorised as a Read tool in the Usaspending MCP Server, which means it retrieves data without modifying state.
Register the Usaspending MCP server in PolicyLayer and add a rule for recipient: 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 Usaspending. Nothing to install.
recipient 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 recipient 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 recipient. 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.
recipient is provided by the Usaspending MCP server (thsmale/usaspending-mcp-server). 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 →