AI agents call board_delete_project to permanently remove resources in Agent Board — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a project and cascades deletion to all associated tasks. Deletion is irreversible and cannot be undone. The blast radius is significant (entire project and tasks lost), warranting high severity. While not financial or involving code execution, it is destructive and represents one of the most severe action categories.
From the tool's definition Tool name is 'board_delete_project' with description 'Delete a project and all its tasks'. The words 'Delete' and 'all its tasks' indicate irreversible removal of data at scale.
Documented attack patterns abuse exactly the kind of access board_delete_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Board, and nothing reaches the server without passing your rules. This is the rule we recommend for board_delete_project:
{
"version": "1",
"default": "deny",
"hide": [
"board_delete_project"
]
} board_delete_project 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.
Delete a project and all its tasks. It is categorised as a Destructive tool in the Agent Board MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Board MCP server in PolicyLayer and add a rule for board_delete_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 Agent Board. Nothing to install.
board_delete_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 board_delete_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 board_delete_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.
board_delete_project is provided by the Agent Board MCP server (quentintou/agent-board). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Board, 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 Agent Board tools catalogued and risk-classified — across an index of 43,000+ MCP servers.