AI agents call count_work_items to retrieve information from Plane without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a count operation on work items, which is a read-only query that retrieves summary data without creating, modifying, or deleting anything. Count operations are non-destructive reads. Low severity because counting data has minimal blast radius—an AI agent misusing this tool would at worst retrieve aggregate statistics, with no side effects.
From the tool's definition Tool name is 'count_work_items' which indicates a counting/query operation. The empty description limits certainty, but the name suggests retrieval of aggregate data without modification.
Attacks that exploit this kind of access
count_work_items. It is categorised as a Read tool in the Plane MCP Server, which means it retrieves data without modifying state.
Register the Plane MCP server in PolicyLayer and add a rule for count_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.
count_work_items 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 count_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 count_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.
count_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 →