Outline MCP Server

🚀 Outline MCP Server Overview

An MCP (Model Context Protocol) server that provides tools for interacting with the Outline API, enabling AI agents to programmatically manage documents, collections, and other entities through the Outline knowledge base platform.

✨ Features

Document Management

• ✅ Create new documents with custom attributes
• ✅ Get document details
• ✅ Update existing documents
• ✅ Delete documents
• ✅ List documents
• ✅ Search documents
• ✅ Ask natural language questions about documents
• ✅ Create templates from existing documents
• ✅ Move documents to different collections or locations
• ✅ Archive documents

Collection Management

• ✅ Get collection details
• ✅ List collections
• ✅ Create and update collections

Comment Management

• ✅ Create comments on documents
• ✅ Update existing comments
• ✅ Delete comments

User Management

• ✅ List and filter users

⚠️ Important Note

The SSE server implementation uses Supergateway to provide a more reliable connection when integrating with Cursor's MCP.

🚀 Quick Start

Prerequisites

• Node.js (v18 or higher)
• An Outline account with API access
• An Outline API key with appropriate permissions

Installation

# Run directly using npx
OUTLINE_API_KEY=… npx outline-mcp-server

# Or install from npm
npm install -g outline-mcp-server
OUTLINE_API_KEY=… outline-mcp-server

# Run on a custom port (default is 6060)
OUTLINE_API_KEY=… outline-mcp-server --port 7070

Environment Variables

• OUTLINE_API_KEY (Required): Your Outline API key.
• OUTLINE_API_URL (Optional): An alternative URL for using an alternate domain name or a self-hosted Outline API.

CLI Options

• --port <number> (Optional): Specify the port on which the server runs (Default: 6060).

Usage

After installation, you can interact with the MCP server using an AI assistant that supports the Model Context Protocol (e.g., Claude via Cursor).

Example queries your AI assistant can now handle:

• "List all documents in my Outline workspaces."
• "Create a new document in the 'Product' collection."
• "Find all documents related to a specific topic."
• "Ask natural language questions about your documents."
• "Create a template from an existing document."
• "Update document content."
• "Add a comment to a document."

📚 Documentation

Development

# Clone this repository
git clone https://github.com/mmmeff/outline-mcp.git
cd outline-mcp

# Install dependencies
npm install

Create a .env file containing your Outline API key:

OUTLINE_API_KEY=your_outline_api_key_here
OUTLINE_API_URL=https://your-outline-instance.com/api  # Optional, defaults to https://app.getoutline.com/api

# Run @modelcontextprotocol/mcp-ai while building/monitoring the project
npm run dev

🤝 Contribution

Contributions are welcome! Please refer to CONTRIBUTING.md.

📄 License

MIT License

📞 Contact

• Author: mmmeff
• Repository: outline-mcp on GitHub