Crea una dependencia entre tareas. type ∈ {FS, SS, FF, SF}.
AI agents use set_dependency to create or update resources in Projectlibre — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Projectlibre environment.
Creating task dependencies is a reversible modification that changes project structure. This is Write category (not Destructive, since dependencies can be removed/modified), with medium severity because incorrect dependencies could disrupt project scheduling and planning, but effects are correctable without data loss.
From the tool's definition Tool creates a dependency between tasks ("Crea una dependencia entre tareas"), modifying task relationships in a ProjectLibre project file.
Attacks that exploit this kind of access
Crea una dependencia entre tareas. type ∈ {FS, SS, FF, SF}. It is categorised as a Write tool in the Projectlibre MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Projectlibre MCP server in PolicyLayer and add a rule for set_dependency: 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.
set_dependency is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_dependency 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 set_dependency. 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.
set_dependency 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.
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 →