US federal government spending awarded to a public company (sourced from USAspending). Pass ticker and optionally a from/to window (YYYY-MM-DD; defaults to ~2 years); returns each award with the recipient (and parent), awarding agency/sub-agency, obligated/outlayed/potential/total values in USD, ...
AI agents call stocks.gov-spending 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 pure data retrieval and analysis of publicly available federal spending information. It accepts a stock ticker and optional date range to return spending records. The description contains no mechanisms for creating, modifying, deleting, or executing operations. The data returned is read-only lookup of historical spending records.
From the tool's definition Tool retrieves and queries government spending data from USAspending public database with optional date filtering. Returns award information, amounts, dates, and performance periods. No parameters allow modification, deletion, or execution of actions.
Attacks that exploit this kind of access
US federal government spending awarded to a public company (sourced from USAspending). Pass ticker and optionally a from/to window (YYYY-MM-DD; defaults to ~2 years); returns each award with the recipient (and parent), awarding agency/sub-agency, obligated/outlayed/potential/total values in USD, action date, and period of performance. Use it to see how much federal money flows to a company. Data b. 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 stocks.gov-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 Mcp. Nothing to install.
stocks.gov-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 stocks.gov-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 stocks.gov-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.
stocks.gov-spending 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 →