scan_board_cleanup
Read-only deep-clean scan: finds likely-duplicate tickets (grouped by title similarity, each group nominating a keeper + removal candidates), stale/placeholder tickets (old Todo items, placeholder titles), open tickets missing a model:/cap: label (FBMCPF-159 intake orchestration guard — nothing s...
This record as markdown: /tools/ai-featureboard-featureboard/scan-board-cleanup.md
What scan_board_cleanup does on FeatureBoard
AI agents call scan_board_cleanup to retrieve information from FeatureBoard without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why scan_board_cleanup is rated Low
Despite the complex analysis it performs, scan_board_cleanup is fundamentally a read-only diagnostic tool that scans and reports on board state. It identifies candidates for cleanup but does not execute any changes itself. The blast radius of misuse is minimal—an AI agent could receive inaccurate scan results but cannot be tricked into destructive actions by this tool alone.
From the tool's definition Tool description explicitly states 'Read-only deep-clean scan' and performs finding/identifying operations: 'finds likely-duplicate tickets', 'finds...stale/placeholder tickets', 'finds...open tickets missing a label'.
Attacks that exploit this kind of access
The rule that runs scan_board_cleanup 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 scan_board_cleanup, this is the rule to start with:
scan_board_cleanup is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect FeatureBoard, apply this rule, and every scan_board_cleanup call is checked against it from then on.
Questions about scan_board_cleanup
Read-only deep-clean scan: finds likely-duplicate tickets (grouped by title similarity, each group nominating a keeper + removal candidates), stale/placeholder tickets (old Todo items, placeholder titles), open tickets missing a model:/cap: label (FBMCPF-159 intake orchestration guard — nothing should sit in the queue without a sub-model orchestration decision), and priority-scaled SLA breaches (FBMCPF-198: high-priority tickets stuck In Progress with no recent work-log activity →. It is categorised as a Read tool in the FeatureBoard MCP Server, which means it retrieves data without modifying state.
Register the FeatureBoard MCP server in PolicyLayer and add a rule for scan_board_cleanup: 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.
scan_board_cleanup 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 scan_board_cleanup 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 scan_board_cleanup. 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.
scan_board_cleanup 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.
This server
Across the catalogue