create_invitation
AI agents use create_invitation to create or update resources in Waldur MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Waldur MCP Server environment.
Creating invitations is a reversible write operation—invitations can typically be cancelled or revoked. It modifies system state by adding a new record but does not delete data or trigger financial transactions.
From the tool's definition Tool name 'create_invitation' indicates it creates a new entity (an invitation). The empty description limits certainty, but the verb 'create' and common patterns in Waldur (a service management platform) suggest this generates a new record in the system.
Attacks that exploit this kind of access
create_invitation. It is categorised as a Write tool in the Waldur MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Waldur MCP Server MCP server in PolicyLayer and add a rule for create_invitation: 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 Waldur MCP Server. Nothing to install.
create_invitation 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 create_invitation 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 create_invitation. 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.
create_invitation is provided by the Waldur MCP Server MCP server (waldur/waldur-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 →