AI agents call todoComments to retrieve information from Ts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though todoComments only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Find all TODO, FIXME, HACK, and other configured comment markers in a file. Returns the location and text of each matching comment. You must provide the descriptors array specifying which markers to search for. It is categorised as a Read tool in the Ts MCP Server, which means it retrieves data without modifying state.
Register the Ts MCP server in PolicyLayer and add a rule for todoComments: 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 Ts. Nothing to install.
todoComments is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the todoComments 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 todoComments. 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.
todoComments is provided by the Ts MCP server (ts-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.