get_bookings
AI agents call get_bookings to retrieve information from Cal Com MCP Server for Customers without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists booking information, which is a read operation with no side effects. The absence of descriptive text slightly lowers confidence, but the naming pattern and server purpose make it clear this is data retrieval rather than creation, modification, or deletion.
From the tool's definition Tool name 'get_bookings' indicates retrieval of booking data. The empty description prevents confirmation of specific parameters, but the verb 'get' and context within a scheduling server (alongside create_booking, list_event_types) strongly suggest this…
Attacks that exploit this kind of access
get_bookings. It is categorised as a Read tool in the Cal Com MCP Server for Customers MCP Server, which means it retrieves data without modifying state.
Register the Cal Com MCP Server for Customers MCP server in PolicyLayer and add a rule for get_bookings: 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 Cal Com MCP Server for Customers. Nothing to install.
get_bookings 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_bookings 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_bookings. 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_bookings is provided by the Cal Com MCP Server for Customers MCP server (niopub/calcom-mcp-for-customers). 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 →