Graduate a project on pmptwiki — archives it with a Hall of Fame badge. The project can no longer be updated. Non-interactive. User must have run
AI agents call pmpt_graduate to permanently remove resources in Pmpt — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Graduating a project permanently prevents future updates, making this an irreversible action. While it doesn't delete data, it irrevocably changes the project's state in a way that cannot be undone, which aligns with the Destructive category. Severity is high because an AI agent misusing this tool would permanently freeze a project, eliminating all future edit capability.
From the tool's definition 'archives it with a Hall of Fame badge. The project can no longer be updated' — this is an irreversible state change that permanently locks the project from further modification.
Documented attack patterns abuse exactly the kind of access pmpt_graduate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pmpt, and nothing reaches the server without passing your rules. This is the rule we recommend for pmpt_graduate:
{
"version": "1",
"default": "deny",
"hide": [
"pmpt_graduate"
]
} pmpt_graduate disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Graduate a project on pmptwiki — archives it with a Hall of Fame badge. The project can no longer be updated. Non-interactive. User must have run. It is categorised as a Destructive tool in the Pmpt MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pmpt MCP server in PolicyLayer and add a rule for pmpt_graduate: 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 Pmpt. Nothing to install.
pmpt_graduate 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 pmpt_graduate 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 pmpt_graduate. 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.
pmpt_graduate is provided by the Pmpt MCP server (pmptwiki/pmpt-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pmpt, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Pmpt tools catalogued and risk-classified — across an index of 43,000+ MCP servers.