AI agents call search_spending to retrieve information from Fec without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing FEC financial disclosure data by spending description or recipient. It has no side effects—it only reads and returns information from the OpenFEC API. Even though the data is financial in nature, the tool itself performs passive query and retrieval, not financial transactions or commitments.
From the tool's definition Tool description uses 'Search' verb and explicitly queries campaign spending data (Schedule B) across committees; no mention of modification, deletion, or execution of operations. Returns spending records for analysis.
Attacks that exploit this kind of access
Search campaign spending (Schedule B) across all committees by description or recipient. Use to find questionable expenditures like. It is categorised as a Read tool in the Fec MCP Server, which means it retrieves data without modifying state.
Register the Fec MCP server in PolicyLayer and add a rule for search_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 Fec. Nothing to install.
search_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 search_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 search_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.
search_spending is provided by the Fec MCP server (sh-patterson/fec-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 →