Evaluate a single response using LLM-as-a-judge with customizable criteria and rubrics
AI agents call judge.evaluate_response to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool evaluates/scores a response using an LLM judge — it reads and assesses input data but does not create, modify, delete, or trigger external side effects. The output is an evaluation result, making it a read/query operation. Severity is low as misuse would at worst produce biased or incorrect evaluations.
From the tool's definition 'Evaluate a single response using LLM-as-a-judge with customizable criteria and rubrics'
Attacks that exploit this kind of access
Evaluate a single response using LLM-as-a-judge with customizable criteria and rubrics. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for judge.evaluate_response: 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 ContextForge MCP Gateway. Nothing to install.
judge.evaluate_response 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 judge.evaluate_response 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 judge.evaluate_response. 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.
judge.evaluate_response is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →