AI agents use manage_milestone_work_items to create or update resources in Plane — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Plane environment.
Without a detailed description, confidence is reduced to 0.7. The name suggests reversible operations (associating/disassociating work items with milestones) rather than deletion or irreversible destruction. This is classified as Write because it modifies project data structure relationships, which affects project planning but remains reversible.
From the tool's definition Tool name 'manage_milestone_work_items' indicates modification of work item associations with milestones. The verb 'manage' typically implies creating, updating, or removing relationships.
Attacks that exploit this kind of access
manage_milestone_work_items. It is categorised as a Write tool in the Plane MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Plane MCP server in PolicyLayer and add a rule for manage_milestone_work_items: 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 Plane. Nothing to install.
manage_milestone_work_items 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 manage_milestone_work_items 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 manage_milestone_work_items. 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.
manage_milestone_work_items is provided by the Plane MCP server (@makeplane/plane-mcp-server). 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 →