eval_report

Compare board-workflow vs chat-workflow trials using label conventions: experiment:board / experiment:chat marks a ticket

SERVERFeatureBoard SOURCEhttps://github.com/valentil/featureboard-mcp/releases/download/v0.7/featureboard.plugin

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/ai-featureboard-featureboard/eval-report.md

WHAT IT DOES

What eval_report does on FeatureBoard

AI agents call eval_report 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.

RISK

Why eval_report is rated Low

The tool compares/analyzes experiment trials by reading labeled tickets. 'Compare' and 'eval' (evaluate) indicate a read/analysis operation with no apparent side effects. No creation, modification, execution, or deletion is described. Severity is low as it only retrieves and analyzes existing data. Confidence is moderate because the description is brief and doesn't explicitly confirm read-only behavior.

From the tool's definition Compare board-workflow vs chat-workflow trials using label conventions

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs eval_report 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_report, this is the rule to start with:

eval_report Allowed

eval_report is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "eval_report": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect FeatureBoard, apply this rule, and every eval_report call is checked against it from then on.

FAQ

Questions about eval_report

What does the eval_report tool do? +

Compare board-workflow vs chat-workflow trials using label conventions: experiment:board / experiment:chat marks a ticket. It is categorised as a Read tool in the FeatureBoard MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on eval_report? +

Register the FeatureBoard MCP server in PolicyLayer and add a rule for eval_report: 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.

What risk level is eval_report? +

eval_report is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit eval_report? +

Yes. Add a rate_limit block to the eval_report 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.

How do I block eval_report completely? +

Set action: deny in the PolicyLayer policy for eval_report. 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.

What MCP server provides eval_report? +

eval_report 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.

KEEP EXPLORING

More on FeatureBoard, and thousands of servers like it.

This server

All 215 FeatureBoard tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →