watch_source_todos
Run finite local source TODO watcher scans. Uses polling, respects .gitignore/excludes, and can dry-run or apply extracted tasks.
This record as markdown: /tools/todos/watch-source-todos.md
What watch_source_todos does on Todos
AI agents invoke watch_source_todos to trigger actions in Todos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why watch_source_todos is rated High
This tool executes a scanning process over local source files and can apply extracted tasks (write side effects). The 'run' and 'apply' semantics place it in Execute, which is more severe than a simple Read. Misuse could result in unintended task creation across a codebase.
From the tool's definition 'Run finite local source TODO watcher scans' and 'can dry-run or apply extracted tasks' — the tool actively runs scans and can apply changes to task data
Attacks that exploit this kind of access
The rule that runs watch_source_todos 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 watch_source_todos, this is the rule to start with:
watch_source_todos stays usable, but rate-capped: a runaway agent can't fire it dozens of times 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 watch_source_todos call is checked against it from then on.
Questions about watch_source_todos
Run finite local source TODO watcher scans. Uses polling, respects .gitignore/excludes, and can dry-run or apply extracted tasks. It is categorised as a Execute tool in the Todos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Todos MCP server in PolicyLayer and add a rule for watch_source_todos: 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.
watch_source_todos is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the watch_source_todos 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 watch_source_todos. 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.
watch_source_todos 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.
Across the catalogue