The government has more than 2,000 unique Federal Accounts,
AI agents call federal_accounts 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.
This tool retrieves or queries publicly available government spending account information from USASPENDING.gov. It has no side effects, does not modify data, execute code, delete resources, or move money. It is a straightforward data retrieval operation consistent with the 'Read' category. Severity is low because misuse would only expose existing public financial data.
From the tool's definition Tool is named 'federal_accounts' and is part of a USASPENDING.gov interaction server described as tracking and querying government spending data. The description indicates it retrieves information about Federal Accounts.
Attacks that exploit this kind of access
The government has more than 2,000 unique Federal Accounts,. 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 federal_accounts: 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.
federal_accounts 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 federal_accounts 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 federal_accounts. 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.
federal_accounts 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 →