Compare two responses and determine which is better using LLM-as-a-judge
AI agents call judge.pairwise_comparison 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 comparison and evaluation of responses, which is fundamentally a retrieval and analysis task. It does not alter state, execute arbitrary code, delete data, or create financial obligations. The output is a judgment/determination based on input analysis, making it a Read operation with low blast radius if misused by an AI agent.
From the tool's definition The tool 'judge.pairwise_comparison' compares two responses and determines which is better using LLM-as-a-judge.
Attacks that exploit this kind of access
Compare two responses and determine which is better 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.pairwise_comparison: 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.pairwise_comparison 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.pairwise_comparison 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.pairwise_comparison. 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.pairwise_comparison 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 →