Fetch full detail for a single roll-call vote, including
AI agents call get_vote to retrieve information from Civic Awareness 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 publicly available legislative voting records. It performs a read-only operation with no side effects, modification of data, code execution, financial impact, or destructive capability. The verb 'fetch' combined with the context of retrieving legislative voting details confirms it is a Read operation. The data retrieved is non-sensitive public legislative information.
From the tool's definition Tool name 'get_vote' and description 'Fetch full detail for a single roll-call vote' indicate retrieval of existing legislative voting data without modification, creation, or deletion.
Attacks that exploit this kind of access
Fetch full detail for a single roll-call vote, including. It is categorised as a Read tool in the Civic Awareness MCP Server, which means it retrieves data without modifying state.
Register the Civic Awareness MCP server in PolicyLayer and add a rule for get_vote: 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 Civic Awareness. Nothing to install.
get_vote 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 get_vote 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 get_vote. 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.
get_vote is provided by the Civic Awareness MCP server (julianken/civic-awareness-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 →