Ruta crítica y holgura (slack) por tarea. Requiere un archivo ya calendarizado.
AI agents call critical_path to retrieve information from Projectlibre without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes scheduling data from an existing project file to calculate the critical path and slack times. It performs no modifications, deletions, or external operations — purely a read/query operation.
From the tool's definition 'Ruta crítica y holgura (slack) por tarea' — computes and returns critical path and slack values per task from an already-scheduled file
Attacks that exploit this kind of access
Ruta crítica y holgura (slack) por tarea. Requiere un archivo ya calendarizado. It is categorised as a Read tool in the Projectlibre MCP Server, which means it retrieves data without modifying state.
Register the Projectlibre MCP server in PolicyLayer and add a rule for 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 Projectlibre. Nothing to install.
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 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 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.
critical_path is provided by the Projectlibre MCP server (osyanne/projectlibre-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
critical_path is one line of Projectlibre's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →