Return meetings that occurred within the last N days, useful for recaps and follow ups.
AI agents call get_recent_meetings 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 historical meeting data without modifying, deleting, or executing anything. It is a straightforward query that returns already-existing records. The blast radius of misuse is minimal—an AI agent could retrieve more meeting data than intended, but cannot alter, delete, or perform external actions.
From the tool's definition Tool description states 'Return meetings that occurred within the last N days' — a retrieval operation with no modification, deletion, or execution.
Attacks that exploit this kind of access
Return meetings that occurred within the last N days, useful for recaps and follow ups. 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 get_recent_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 Granola MCP Server. Nothing to install.
get_recent_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 get_recent_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 get_recent_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.
get_recent_meetings is provided by the Granola MCP Server MCP server (pavitarsaini/granola-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 →