AI agents call gov.senate-votes 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 queries historical voting records from a public government database and returns filtered results. It has no capability to modify records, execute operations, move funds, or trigger side effects. The filtering parameters (congress, session, result, document) are typical of read-only query construction.
From the tool's definition Tool description states it retrieves 'US Senate roll-call votes' from senate.gov with filtering options. No language indicates data creation, modification, deletion, code execution, or financial transactions.
Attacks that exploit this kind of access
US Senate roll-call votes, newest first. Locally aggregated daily from senate.gov. Filter by congress, session (1|2), result, document (e.g.,. 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.senate-votes: 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.senate-votes 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.senate-votes 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.senate-votes. 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.senate-votes 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 →