Get an AI-generated plain language summary of a bill.
AI agents call get_bill_summary to retrieve information from Umbrella Terminal 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 presents existing bill summary data without side effects. It performs a straightforward read operation on Colorado legislative intelligence. No data is modified, deleted, or executed. The severity is low because misuse (e.g., an agent requesting summaries of many bills) has minimal blast radius—it only retrieves publicly available legislative information.
From the tool's definition Tool name 'get_bill_summary' and description 'Get an AI-generated plain language summary of a bill' indicate retrieval of legislative information.
Attacks that exploit this kind of access
Get an AI-generated plain language summary of a bill. It is categorised as a Read tool in the Umbrella Terminal MCP MCP Server, which means it retrieves data without modifying state.
Register the Umbrella Terminal MCP server in PolicyLayer and add a rule for get_bill_summary: 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 Umbrella Terminal MCP. Nothing to install.
get_bill_summary 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_bill_summary 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_bill_summary. 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_bill_summary is provided by the Umbrella Terminal MCP server (theblackcompany/umbrella_terminal_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 →