search_summaries
AI agents call search_summaries 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.
The tool name 'search_summaries' indicates querying/searching legislative summaries. All sibling tools on this server are Read operations that retrieve legislative data without modification. The server's purpose is to enable analysis of legislative intelligence, campaign finance, and voting records—all informational.
From the tool's definition Tool name 'search_summaries' and context of legislative intelligence tools (all sibling tools are read-only queries like get_bill, get_bill_amendments, get_bill_history).
Attacks that exploit this kind of access
search_summaries. 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 search_summaries: 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.
search_summaries 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 search_summaries 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 search_summaries. 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.
search_summaries 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 →