This record as markdown: /tools/todos/update-watch-rule.md
What update_watch_rule does on Todos
AI agents use update_watch_rule 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 update_watch_rule is rated Medium
This tool modifies existing watch rules (a reversible write operation) rather than reading, executing arbitrary commands, or destructively deleting data. The impact is localized to terminal watch configuration.
From the tool's definition Tool name 'update_watch_rule' and description 'Update a local terminal watch rule' indicate modification of existing configuration/rules data.
Attacks that exploit this kind of access
The rule that runs update_watch_rule 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 update_watch_rule, this is the rule to start with:
update_watch_rule 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 update_watch_rule call is checked against it from then on.
Questions about update_watch_rule
Update a local terminal watch rule. 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 update_watch_rule: 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.
update_watch_rule 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_watch_rule 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_watch_rule. 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_watch_rule 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