AI agents use set_stage to create or update resources in Proofhub — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Proofhub environment.
Moving a task to a different stage updates task metadata and workflow state, constituting a write operation. It is reversible (tasks can be moved back), so it does not qualify as Destructive. The blast radius is medium because incorrect stage movements could disrupt project workflow and task visibility, but changes are easily undone.
From the tool's definition Tool description states 'Move a task to a specific stage' which modifies the state/position of a task within a project workflow. This is a reversible state change operation.
Attacks that exploit this kind of access
Move a task to a specific stage (board column) by stage name or numeric id. project and todolist default to context. It is categorised as a Write tool in the Proofhub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Proofhub MCP server in PolicyLayer and add a rule for set_stage: 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 Proofhub. Nothing to install.
set_stage 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_stage 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_stage. 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_stage is provided by the Proofhub MCP server (yashmody/proofhub-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 →