Measure agreement between different judges and human evaluators
AI agents call calibration.test_judge_agreement 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 performs a read-only analytical operation—it measures and evaluates agreement metrics between judges. It does not create, modify, or delete data; it does not execute code or external commands; and it does not commit financial obligations. The function is purely observational and informational, consistent with the 'Read' category for data retrieval and query operations.
From the tool's definition Tool name 'calibration.test_judge_agreement' and description 'Measure agreement between different judges and human evaluators' indicate a measurement or analysis operation that retrieves and compares existing evaluation data without modifying, executing…
Attacks that exploit this kind of access
Measure agreement between different judges and human evaluators. 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 calibration.test_judge_agreement: 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.
calibration.test_judge_agreement 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 calibration.test_judge_agreement 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 calibration.test_judge_agreement. 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.
calibration.test_judge_agreement 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 →