This data can be used to drill down into specific subsets of data by level of detail.
AI agents call spending 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 queries government spending information from a public data source. There is no indication of write, delete, execute, or financial operations. The description explicitly frames this as data exploration and drilling down into subsets, which are read operations. Severity is low because it only accesses public government spending data with no destructive or financial consequences.
From the tool's definition Tool name 'spending' and description states 'This data can be used to drill down into specific subsets of data by level of detail' — describes querying/exploring government spending data with no modification or side effects.
Attacks that exploit this kind of access
This data can be used to drill down into specific subsets of data by level of detail. 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 spending: 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.
spending 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 spending 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 spending. 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.
spending 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 →