Skip to main content
Moxn is a knowledge base designed for AI agents. Most teams keep docs in wikis, Google Drive, or Notion — and end up copy-pasting into prompts or building RAG pipelines just to give agents access. Moxn gives your agents direct, structured access to your docs over MCP or CLI. No exports, no embeddings, no custom integrations.
Moxn Knowledge Base

Choose Your Setup

Pick the connection method that fits your workflow:
CLIMCP
AuthAPI key (MOXN_API_KEY)Browser-based OAuth
Setupnpm install + install-skillConfig snippet in MCP settings
Best forClaude Code, Codex, Cursor, and other coding agentsClaude.ai, ChatGPT, Gemini, desktop apps
How it worksAgent calls knowledge-base commands directlyAgent uses MCP tools

Built for Agents

Agents connect to Moxn and get structured access to your knowledge base through a standard tool interface: find, read, search, documents, and sections.

Search and read

Agents query your docs for context, grounding responses in your team’s actual knowledge instead of stale training data.

Write on branches

When you ask an agent to create or update content, it works on a branch. You review the diff and merge when ready.

Control visibility

Section-level permissions let you hide sensitive content (API keys, credentials, internal metrics) from agents while keeping it visible to your team.

Any MCP host

Claude.ai, ChatGPT, Gemini, Claude Code, Cursor, Claude Desktop, and any other MCP-compatible client.

A Real Editor for Your Team

Moxn isn’t just an API for agents — it’s a full-featured editor for your team. Rich text, code blocks with syntax highlighting, mermaid diagrams, inline comments, and drag-and-drop section reordering.
Moxn document editor with sections, code blocks, and mermaid diagrams
Your team writes and edits documentation in the web app. Agents read and write the same content over MCP. Everyone works from a single source of truth.

Bring Your Existing Docs

Import from Notion with full fidelity — pages, databases, properties, and cross-references come through intact. Or import local markdown and CSV files.
For AI tools: This documentation is available as llms.txt and llms-full.txt for LLM consumption.