search_by_person
AI agents call search_by_person to retrieve information from Granola MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries meeting data filtered by person/attendee. It performs a read-only search operation with no capability to modify, delete, or execute external code. The blast radius of misuse is minimal—an agent could access meeting information but cannot alter, destroy, or act on it.
From the tool's definition Tool name 'search_by_person' and server description stating it 'supports filtering by date or attendee' indicates this searches/queries existing meeting notes.
Attacks that exploit this kind of access
search_by_person. It is categorised as a Read tool in the Granola MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Granola MCP Server MCP server in PolicyLayer and add a rule for search_by_person: 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 Granola MCP Server. Nothing to install.
search_by_person 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_by_person 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_by_person. 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_by_person is provided by the Granola MCP Server MCP server (nimblebraininc/mcp-granola). 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 →