Invite a user to collaborate on a project by email. The invitee will receive an email notification.
AI agents use todoist_project_invite to create or update resources in Mcp Todoist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Todoist environment.
This tool creates/modifies state by sending an invitation and establishing a new user relationship on a project. It's reversible (the invitation can be declined or the user removed later), so it doesn't qualify as Destructive. It doesn't execute arbitrary code or move money, so Execute and Financial don't apply.
From the tool's definition Tool performs 'Invite a user to collaborate on a project by email' — creates a new collaboration invitation record in Todoist.
Attacks that exploit this kind of access
Invite a user to collaborate on a project by email. The invitee will receive an email notification. It is categorised as a Write tool in the Mcp Todoist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Todoist MCP server in PolicyLayer and add a rule for todoist_project_invite: 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 Mcp Todoist. Nothing to install.
todoist_project_invite 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 todoist_project_invite 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 todoist_project_invite. 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.
todoist_project_invite is provided by the Mcp Todoist MCP server (@greirson/mcp-todoist). 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 →