Check for disparate impacts across protected groups in outcomes
AI agents call bias.evaluate_outcome_equity 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 an analysis or audit of outcomes to detect bias across protected groups. It queries or examines existing data to identify patterns of disparate impact, which is a non-destructive, non-side-effect operation. No creation, modification, deletion, code execution, or financial transaction occurs. This is a classic Read category use case: data retrieval and analysis for reporting purposes.
From the tool's definition Tool name and description indicate a check/evaluation operation: 'evaluate_outcome_equity' and 'Check for disparate impacts.' The verb 'check' and 'evaluate' are read-only operations that analyze data without modifying, deleting, executing external code, or…
Attacks that exploit this kind of access
Check for disparate impacts across protected groups in outcomes. 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 bias.evaluate_outcome_equity: 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.
bias.evaluate_outcome_equity 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 bias.evaluate_outcome_equity 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 bias.evaluate_outcome_equity. 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.
bias.evaluate_outcome_equity 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 →