request_meeting
AI agents use request_meeting to create or update resources in Schedulia MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Schedulia MCP environment.
Based on the tool name and server context (scheduling assistant that sends meeting invitations), 'request_meeting' most likely creates a new meeting request or sends an invitation, which is a Write operation. Confidence is reduced due to the empty description. Severity is medium as misuse could send unwanted meeting requests to participants.
From the tool's definition Tool name 'request_meeting' on a meeting scheduling server; description is empty and uninformative.
Attacks that exploit this kind of access
request_meeting. It is categorised as a Write tool in the Schedulia MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Schedulia MCP server in PolicyLayer and add a rule for request_meeting: 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 Schedulia MCP. Nothing to install.
request_meeting is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the request_meeting 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 request_meeting. 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.
request_meeting is provided by the Schedulia MCP server (watanka/schedulia-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 →