AI agents call get_dependency_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 tool reads task dependency data to compute and return the critical path—which tasks are blocking downstream work. It performs no modifications, deletions, or external executions. It is a pure read/query operation on existing task data, making it a Read category tool with low severity since misuse would only expose task structure information without side effects.
From the tool's definition Tool name 'get_dependency_critical_path' and description 'Critical path — tasks blocking the most downstream work' indicate a query operation that retrieves and analyzes task dependency information to identify blocking tasks.
Attacks that exploit this kind of access
Critical path — tasks blocking the most downstream work. 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_dependency_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_dependency_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_dependency_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_dependency_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_dependency_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 →