AI agents call gov.congress-amendment 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 publicly available information about US Congressional amendments without creating, modifying, deleting, or executing any actions. The 'lookup or list' language and reference to Congress.gov (a public database) indicate read-only querying. No side effects or state changes occur.
From the tool's definition Tool performs 'lookup or list' of Congressional amendments from Congress.gov, with no modification capabilities mentioned. Returns publicly available government data.
Attacks that exploit this kind of access
US Congressional amendments lookup or list (Congress.gov). Types: hamdt (House), samdt (Senate), suamdt (Senate Unprinted). Pass congress+type+number for single amendment. 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.congress-amendment: 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.congress-amendment 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.congress-amendment 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.congress-amendment. 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.congress-amendment 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 →