remove_project
AI agents call remove_project to permanently remove resources in Metis Public Health — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'remove_project' strongly suggests irreversible deletion of project data. Although the description is empty (lowering confidence slightly from critical to high), the destructive intent is clear from the tool name alone. In a research/knowledge management context like Metis, removing a project would likely destroy associated indexed data, citations, and tracked information.
From the tool's definition Tool name is 'remove_project' which indicates deletion or removal of a project entity, with no reversibility implied.
Attacks that exploit this kind of access
remove_project. It is categorised as a Destructive tool in the Metis Public Health MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for remove_project: 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 Metis Public Health. Nothing to install.
remove_project is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_project 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 remove_project. 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.
remove_project is provided by the Metis Public Health MCP server (sveritg/metis_ph). 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 →