Quickly add a task using natural language
AI agents use quick-add-task to create or update resources in Todoist MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todoist MCP environment.
This tool creates new tasks, which is a reversible write operation. It modifies the task database by adding entries but does not delete, execute arbitrary code, or move money. Severity is medium because task creation is low-risk if misused (tasks can be deleted), but an agent could spam or create many unwanted tasks. Confidence is high because the intent is explicit and unambiguous.
From the tool's definition Tool name is 'quick-add-task' and description states 'Quickly add a task using natural language' — directly creates new task data in Todoist.
Attacks that exploit this kind of access
Quickly add a task using natural language. It is categorised as a Write tool in the Todoist MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todoist MCP server in PolicyLayer and add a rule for quick-add-task: 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 Todoist MCP. Nothing to install.
quick-add-task 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 quick-add-task 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 quick-add-task. 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.
quick-add-task is provided by the Todoist MCP server (miottid/todoist-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 →