Search meetings by title, content, or participants
AI agents call search_meetings to retrieve information from GranolaAI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing meeting data to find records matching specified criteria. It retrieves information without creating, modifying, deleting, or executing operations. The action is read-only and poses minimal risk even if misused by an AI agent, as it only surfaces existing data the user likely has legitimate access to through Granola.ai.
From the tool's definition The tool description explicitly states it 'search[es] meetings by title, content, or participants' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Search meetings by title, content, or participants. It is categorised as a Read tool in the GranolaAI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GranolaAI MCP Server MCP server in PolicyLayer and add a rule for search_meetings: 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 GranolaAI MCP Server. Nothing to install.
search_meetings 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_meetings 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_meetings. 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_meetings is provided by the GranolaAI MCP Server MCP server (proofsh/granola-mcp-server). 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 →