Search for federal contract awards. Date filtering searches for awards that had ANY transaction activity (modifications, obligations, payments) during the date range - this includes both new awards and existing awards with recent modifications. For finding only newly signed awards, use the search...
AI agents call search_awards to retrieve information from USASpending MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only operations on publicly available government contract data. It searches, filters, and retrieves information about federal awards without creating, modifying, deleting, or executing any operations. The worst-case misuse would be unauthorized information gathering, which poses minimal risk since the underlying data (USASpending.gov) is public. Classification as Read is appropriate.
From the tool's definition Tool name is 'search_awards' and description states it 'Search[es] for federal contract awards' with date filtering and transaction activity queries. No modification, deletion, or execution capabilities are mentioned.
Attacks that exploit this kind of access
Search for federal contract awards. Date filtering searches for awards that had ANY transaction activity (modifications, obligations, payments) during the date range - this includes both new awards and existing awards with recent modifications. For finding only newly signed awards, use the search_new_awards tool instead. It is categorised as a Read tool in the USASpending MCP Server MCP Server, which means it retrieves data without modifying state.
Register the USASpending MCP Server MCP server in PolicyLayer and add a rule for search_awards: 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 MCP Server. Nothing to install.
search_awards 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 search_awards 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 search_awards. 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.
search_awards is provided by the USASpending MCP Server MCP server (khowabunga/usaspending-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 →