AI agents call gov.fec-expenditures 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 retrieves and queries historical FEC financial disclosure data without modifying, deleting, or executing external operations. It presents no destructive or financial risk—it only reads already-public political finance records. Confidence is high because the description clearly indicates data retrieval with no side effects. Severity is low because misuse would simply return filtered subsets of public data.
From the tool's definition Tool queries "FEC Schedule B — itemized committee disbursements" with filtering by committeeId, recipient name/city/state, disbursement purpose, description, amount, date ranges, and cycle.
Attacks that exploit this kind of access
FEC Schedule B — itemized committee disbursements (>157M rows). Filter by committeeId, recipient name/city/state, disbursement purpose category, description, amount + date ranges, cycle. 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 gov.fec-expenditures: 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.
gov.fec-expenditures 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 gov.fec-expenditures 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 gov.fec-expenditures. 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.
gov.fec-expenditures 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 →