prune_board
Guarded cleanup: deletes ONLY the ticket ids you pass, and only when confirm is true (otherwise returns a dry-run preview of what would be deleted). Non-existent ids are reported, not fatal. Pair with scan_board_cleanup
This record as markdown: /tools/ai-featureboard-featureboard/prune-board.md
What prune_board does on FeatureBoard
AI agents call prune_board to permanently remove resources in FeatureBoard, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why prune_board is rated Critical
The tool permanently deletes tickets when confirm=true. Despite the guarded dry-run mode, the actual operation is irreversible deletion of board tickets, making it Destructive. The high severity reflects that an AI agent could pass multiple ticket IDs and confirm=true, resulting in permanent loss of multiple work items.
From the tool's definition "deletes ONLY the ticket ids you pass" and "only when confirm is true (otherwise returns a dry-run preview of what would be deleted)"
Attacks that exploit this kind of access
The rule that runs prune_board safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FeatureBoard, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For prune_board, this is the rule to start with:
prune_board is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect FeatureBoard, apply this rule, and every prune_board call is checked against it from then on.
Questions about prune_board
Guarded cleanup: deletes ONLY the ticket ids you pass, and only when confirm is true (otherwise returns a dry-run preview of what would be deleted). Non-existent ids are reported, not fatal. Pair with scan_board_cleanup. It is categorised as a Destructive tool in the FeatureBoard MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the FeatureBoard MCP server in PolicyLayer and add a rule for prune_board: 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 FeatureBoard. Nothing to install.
prune_board 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 prune_board 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 prune_board. 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.
prune_board is provided by the FeatureBoard MCP server (https://github.com/valentil/featureboard-mcp/releases/download/v0.7/featureboard.plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FeatureBoard, and thousands of servers like it.
Across the catalogue