eval_model_matrix
FBMCPF-148 — run a ticket
This record as markdown: /tools/ai-featureboard-featureboard/eval-model-matrix.md
What eval_model_matrix does on FeatureBoard
AI agents invoke eval_model_matrix to trigger actions in FeatureBoard. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why eval_model_matrix is rated High
The description 'run a ticket' indicates this tool executes some process or workflow associated with a ticket. This falls under Execute since it triggers external operations. Confidence is moderate because the description is vague and doesn't specify exact actions, but 'run' strongly implies execution.
From the tool's definition 'run a ticket' — the tool executes a ticket/task, implying it triggers operations or processes defined by the ticket arguments
Attacks that exploit this kind of access
The rule that runs eval_model_matrix 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 eval_model_matrix, this is the rule to start with:
eval_model_matrix stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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 eval_model_matrix call is checked against it from then on.
Questions about eval_model_matrix
FBMCPF-148 — run a ticket. It is categorised as a Execute tool in the FeatureBoard MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FeatureBoard MCP server in PolicyLayer and add a rule for eval_model_matrix: 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.
eval_model_matrix is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the eval_model_matrix 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 eval_model_matrix. 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.
eval_model_matrix 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