Skip to content

Xybern Documentation

Xybern is the authorisation and privacy layer for enterprise AI agents, plus the vertical AI products built on top of it. Get an overview of the platform, its APIs, and how to put every agent action behind proof of authorisation.

Products

  • Authorisation Layer

    Every agent action (tool calls, delegations, API requests) is intercepted, evaluated against your rules, and allowed or denied before execution, with a full receipt trail.

    Overview

  • Redact

    A drop-in privacy proxy that anonymises PII before it reaches any LLM and de-anonymises the response. Change one line, the base_url.

    Overview

Start building

  • Getting Started

    Base URL, authentication, and SDK setup to make your first authorised call.

    Introduction

  • MCP Server

    Connect Claude, Cursor, and other MCP clients to Xybern with a zero-friction setup.

    MCP Server

  • LLM Gateway

    Put any LLM provider behind the Authorisation Layer and see exactly what gets enforced.

    LLM Gateway

  • Resources

    Error handling, caching, and human-in-the-loop patterns for production deployments.

    Resources

Base URL

All API requests are made to https://www.xybern.com/api/v1.