routing_scorecard
Which model tier should actually run your tickets, measured instead of guessed (FBMCPF-351). Scores every Done ticket from data the board
This record as markdown: /tools/ai-featureboard-featureboard/routing-scorecard.md
What routing_scorecard does on FeatureBoard
AI agents call routing_scorecard 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 routing_scorecard is rated Low
The tool reads completed ticket data and computes a scoring/routing recommendation. It measures rather than modifies, making it a read/query operation. Severity is low because it only surfaces analytical output with no side effects on external systems.
From the tool's definition 'Scores every Done ticket from data the board' — reads and analyzes existing ticket data to produce a scorecard/recommendation; no mention of writing, executing, or deleting anything.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs routing_scorecard 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 routing_scorecard, this is the rule to start with:
routing_scorecard 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 routing_scorecard call is checked against it from then on.
Questions about routing_scorecard
Which model tier should actually run your tickets, measured instead of guessed (FBMCPF-351). Scores every Done ticket from data the board. 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 routing_scorecard: 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.
routing_scorecard 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 routing_scorecard 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 routing_scorecard. 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.
routing_scorecard 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