This MCP server enables AI assistants to interact with Outline document services, creating a bridge between natural language requests and Outline's document management capabilities. It allows for searching, reading, creating, and editing documents, as well as managing collections and comments.
The recommended way to run the MCP Outline server is using Docker to avoid installing dependencies directly on your machine.
docker buildx build -t mcp-outline .
{
"mcpServers": {
"mcp-outline": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"-e",
"DOCKER_CONTAINER=true",
"-e",
"OUTLINE_API_KEY",
"-e",
"OUTLINE_API_URL",
"mcp-outline"
],
"env": {
"OUTLINE_API_KEY": "<YOUR_OUTLINE_API_KEY>",
"OUTLINE_API_URL": "<YOUR_OUTLINE_API_URL>"
}
}
}
}
If you prefer not to use Docker, you can install the server directly:
Ensure you have Python 3.10 or higher installed
Create a .env
file with your Outline API credentials:
OUTLINE_API_KEY=your_outline_api_key_here
OUTLINE_API_URL=https://app.getoutline.com/api
Note: The OUTLINE_API_URL
is optional and defaults to https://app.getoutline.com/api
. For self-hosted Outline instances, specify your custom URL.
Install and run the server:
uv pip install -e ".[dev]"
mcp dev src/mcp_outline/server.py
The MCP Outline server supports various commands for interacting with your Outline documents. Here are some examples of what you can do:
Search for documents using natural language:
Search for documents containing "project planning"
List all available collections to see your document structure:
Show me all available collections
Access document content by specifying its ID:
Get the content of document with ID "docId123"
Create new documents in specific collections:
Create a new document titled "Research Report" in collection "colId456" with content "# Introduction\n\nThis is a research report..."
Add comments to existing documents:
Add a comment to document "docId123" saying "This looks great, but we should add more details to the methodology section."
Reorganize your documents between collections:
Move document "docId123" to collection "colId789"
See which documents link to a specific document:
Show me all backlinks to document "docId123"
To debug the Docker image using the MCP inspector:
npx @modelcontextprotocol/inspector docker run -i --rm --init -e DOCKER_CONTAINER=true --env-file .env mcp-outline
When using the MCP Inspector, navigate to Tools > Click on a tool to make it appear on the right side panel, allowing you to query it directly.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "mcp-outline" '{"command":"docker","args":["run","-i","--rm","--init","-e","DOCKER_CONTAINER=true","-e","OUTLINE_API_KEY","-e","OUTLINE_API_URL","mcp-outline"],"env":{"OUTLINE_API_KEY":"<YOUR_OUTLINE_API_KEY>","OUTLINE_API_URL":"<YOUR_OUTLINE_API_URL>"}}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"mcp-outline": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"-e",
"DOCKER_CONTAINER=true",
"-e",
"OUTLINE_API_KEY",
"-e",
"OUTLINE_API_URL",
"mcp-outline"
],
"env": {
"OUTLINE_API_KEY": "<YOUR_OUTLINE_API_KEY>",
"OUTLINE_API_URL": "<YOUR_OUTLINE_API_URL>"
}
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"mcp-outline": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"-e",
"DOCKER_CONTAINER=true",
"-e",
"OUTLINE_API_KEY",
"-e",
"OUTLINE_API_URL",
"mcp-outline"
],
"env": {
"OUTLINE_API_KEY": "<YOUR_OUTLINE_API_KEY>",
"OUTLINE_API_URL": "<YOUR_OUTLINE_API_URL>"
}
}
}
}
3. Restart Claude Desktop for the changes to take effect