🧭 PROACTIVE ETHICAL GUIDANCE - Call this tool when you need ethical advice for complex scenarios or dilemmas. USE WHEN: (1) Facing ethical dilemmas or moral questions, (2) Need guidance on best practices for sensitive situations, (3) Planning actions that could have ethical implications, (4) See...
AI agents call ethics_guide 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 analyzes ethical frameworks to inform decision-making. It is purely advisory—returning guidance without side effects. Even if an AI agent misuses it by requesting unethical advice, the tool itself only reads/queries; it cannot enforce or execute harmful actions.
From the tool's definition Tool description states it provides 'ethical advice,' 'guidance,' and 'framework-based ethical analysis'—all read/query operations. No mention of modifying data, executing code, deleting content, or financial transactions.
Attacks that exploit this kind of access
🧭 PROACTIVE ETHICAL GUIDANCE - Call this tool when you need ethical advice for complex scenarios or dilemmas. USE WHEN: (1) Facing ethical dilemmas or moral questions, (2) Need guidance on best practices for sensitive situations, (3) Planning actions that could have ethical implications, (4) Seeking framework-based ethical analysis, (5) Need help navigating stakeholder conflicts or competing values. REQUIRED:. 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 ethics_guide: 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.
ethics_guide 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 ethics_guide 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 ethics_guide. 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.
ethics_guide 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 →