Evaluate response against a gold standard reference using LLM-as-a-judge
AI agents call judge.evaluate_with_reference 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.
The tool performs evaluation by comparing a response to a reference answer using an LLM judge. This is a read/query operation with no side effects — it produces a score or judgment but does not modify, delete, or create persistent data. Severity is low as misuse would at most produce misleading evaluation scores.
From the tool's definition 'Evaluate response against a gold standard reference' — this is an assessment/scoring operation that reads/compares data
Attacks that exploit this kind of access
Evaluate response against a gold standard reference using LLM-as-a-judge. 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_with_reference: 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_with_reference 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_with_reference 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_with_reference. 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_with_reference 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.
judge.evaluate_with_reference is one line of ContextForge MCP Gateway's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →