🧠 CONFIRMATION BIAS & CRITICAL THINKING ANALYSIS - Call this tool to analyze AI responses for confirmation bias and intellectual rigor. USE WHEN: (1) An AI response seems overly agreeable or one-sided, (2) You suspect confirmation bias in an AI
AI agents call critical_thinking to retrieve information from Ethics Check MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and examines conversation content to assess philosophical rigor and bias patterns. It has no side effects beyond generating analytical output. The tool does not execute code, modify data, delete content, move money, or trigger external operations. It is purely informational/advisory in nature, making it a Read-category risk.
From the tool's definition Tool analyzes AI responses for confirmation bias and intellectual rigor; described as performing analysis and scanning conversations.
Attacks that exploit this kind of access
🧠 CONFIRMATION BIAS & CRITICAL THINKING ANALYSIS - Call this tool to analyze AI responses for confirmation bias and intellectual rigor. USE WHEN: (1) An AI response seems overly agreeable or one-sided, (2) You suspect confirmation bias in an AI. It is categorised as a Read tool in the Ethics Check MCP MCP Server, which means it retrieves data without modifying state.
Register the Ethics Check MCP server in PolicyLayer and add a rule for critical_thinking: 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 Ethics Check MCP. Nothing to install.
critical_thinking 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 critical_thinking 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 critical_thinking. 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.
critical_thinking is provided by the Ethics Check MCP server (r-huijts/ethics-check-mcp). 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 →