graph_search
AI agents call graph_search 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 appears to search or traverse a graph structure containing legislative data. Graph search operations are read-only queries with no side effects—they retrieve or navigate existing data without modification, deletion, or execution of external code.
From the tool's definition Tool name 'graph_search' and sibling tools (batch_get_entities, batch_get_neighbors, find_path, get_bill, get_bill_amendments, etc.) all indicate querying/retrieval operations.
Attacks that exploit this kind of access
graph_search. 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 graph_search: 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.
graph_search 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 graph_search 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 graph_search. 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.
graph_search 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 →