record_task_review
Record local task review approval, requested changes, or reopen state.
This record as markdown: /tools/todos/record-task-review.md
What record_task_review does on Todos
AI agents use record_task_review to create or update resources in Todos, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
Why record_task_review is rated Medium
This tool writes/updates review state for a task (approval, change requests, or reopen), which is a reversible modification to task metadata. It does not execute code, delete data, or involve financial transactions.
From the tool's definition Record local task review approval, requested changes, or reopen state
Attacks that exploit this kind of access
The rule that runs record_task_review safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Todos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For record_task_review, this is the rule to start with:
record_task_review stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Todos, apply this rule, and every record_task_review call is checked against it from then on.
Questions about record_task_review
Record local task review approval, requested changes, or reopen state. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for record_task_review: 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 Todos. Nothing to install.
record_task_review 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 record_task_review 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 record_task_review. 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.
record_task_review is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Todos, and thousands of servers like it.
This server
Across the catalogue