Undo the last Taskwarrior operation.
AI agents use taskwarrior_undo to create or update resources in Taskwarrior MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Taskwarrior MCP Server environment.
This tool reverses the most recent Taskwarrior operation, which could restore deleted tasks, revert modifications, or undo completions. While it reverses changes (making it a form of write/modify), it is itself a reversible operation in the sense that data is being restored rather than permanently destroyed. It fits best under Write since it modifies task state.
From the tool's definition Undo the last Taskwarrior operation
Attacks that exploit this kind of access
Undo the last Taskwarrior operation. It is categorised as a Write tool in the Taskwarrior MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Taskwarrior MCP Server MCP server in PolicyLayer and add a rule for taskwarrior_undo: 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 Taskwarrior MCP Server. Nothing to install.
taskwarrior_undo 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 taskwarrior_undo 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 taskwarrior_undo. 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.
taskwarrior_undo is provided by the Taskwarrior MCP Server MCP server (tylyan/taskwarrior-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 →