AI agents call get_critical_path to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that analyzes task relationships and dependencies to identify critical path elements. There are no side effects, no data modification, no code execution, and no destructive actions. The tool retrieves and processes existing task information to provide insights, making it a Read category risk with low severity since misuse would only result in viewing analytical data.
From the tool's definition The tool performs analysis on existing task data to 'find tasks that block the most downstream work' without modifying, deleting, or executing any operations. It is purely informational/analytical in nature.
Attacks that exploit this kind of access
Find tasks that block the most downstream work (critical path analysis). It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for get_critical_path: 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.
get_critical_path 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 get_critical_path 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 get_critical_path. 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.
get_critical_path 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.
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 →