Score a single AI-generated output against a named rubric (jira-ticket, code-review, email-draft, sql-query, documentation, summary). Returns a numeric score with per-criterion breakdown.
AI agents call eval_score to retrieve information from Scan Your Ai Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
eval_score performs a passive assessment of AI outputs against predefined rubrics. It queries/retrieves scoring information and returns numeric results with no side effects, data modification, code execution, deletion, or financial impact. This clearly fits the Read category as it is a query/analysis operation.
From the tool's definition Tool description states 'Score a single AI-generated output against a named rubric... Returns a numeric score with per-criterion breakdown.' This is a read-only evaluation operation that retrieves scoring data without modifying any underlying systems or…
Attacks that exploit this kind of access
Score a single AI-generated output against a named rubric (jira-ticket, code-review, email-draft, sql-query, documentation, summary). Returns a numeric score with per-criterion breakdown. It is categorised as a Read tool in the Scan Your Ai Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Scan Your Ai Toolkit MCP server in PolicyLayer and add a rule for eval_score: 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 Scan Your Ai Toolkit. Nothing to install.
eval_score 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 eval_score 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_score. 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_score is provided by the Scan Your Ai Toolkit MCP server (sakthivelchan89/scan_your_ai_toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →