Update a task in Todoist
AI agents use update-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.
The tool modifies task data reversibly—updates can be undone by subsequent updates or edits. This is a Write operation rather than Execute (no code/command execution) or Destructive (reversible, not permanent deletion). Severity is medium because erroneous mass updates could disrupt a user's task list, but the effects are recoverable and the blast radius is limited to task metadata/state within a single platform.
From the tool's definition Tool name 'update-task' and description 'Update a task in Todoist' indicate modification of existing data. Sibling tools include 'add-task', 'close-task', and 'delete-project', confirming this server manages task state changes.
Attacks that exploit this kind of access
Update a task in Todoist. 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 update-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.
update-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 update-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 update-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.
update-task is provided by the Todoist MCP server (scofieldkoh/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 →