On this page
Docs
Remote MCP
How Ethics of AI runs a remote Model Context Protocol server: the auth flow, the tool surface, and the deployment trade-offs behind it.
Docs in this topic
Meeting users where they are: why we built MCP
Browsers are one user surface; AI clients are another. MCP lets people engage with Ethics of AI from inside the client they already use.
Connect your AI client to Ethics of AI
Add the Ethics of AI MCP connector in Claude Desktop, on claude.ai, or on mobile, so Claude can drive assessments and read your account on your behalf.
Assistive, not autopilot: how interactive assessments stay yours
Claude can explain each assessment question in plain English, but it cannot pick or write your answer. This is how that line is drawn, and why it still needs your trust.
How we built a remote MCP server for Ethics of AI
Why remote MCP, how DCR with Clerk works, why we wrap our existing API instead of going pure-MCP, and why API Gateway plus Lambda plus FastMCP is the right surface for us.