MCP Hub
Back to servers

outline-smart-mcp

A sophisticated Outline Wiki integration that adds AI-powered 'Smart Features' like RAG-based Q&A, semantic search, and automatic summarization alongside standard CRUD operations.

Tools
37
Updated
Jan 12, 2026

Outline Wiki MCP Server

npm version License: MIT

English | 한국어 | 日本語 | 中文

A Model Context Protocol (MCP) server that enables LLMs to interact with Outline wiki through structured API calls. This server provides document management, search, collections, comments, and AI-powered smart features including RAG-based Q&A.

Why This Server?

Most Outline MCP servers provide basic API wrappers. This one adds optional Smart Features:

FeatureWhat it does
ask_wikiAsk questions in natural language, get answers based on your wiki content (RAG)
find_relatedFind semantically similar documents, not just keyword matches
summarize_documentGenerate summaries of long documents
suggest_tagsGet tag suggestions based on content analysis

When you might need this:

  • Your team's wiki has grown large and search isn't enough
  • You want to query your documentation conversationally
  • You need semantic search across your knowledge base

When basic MCP is sufficient:

  • You only need CRUD operations on documents
  • You don't want to set up OpenAI API
  • Your wiki is small and well-organized

Smart features require ENABLE_SMART_FEATURES=true and an OpenAI API key. Without these, the server works as a standard Outline MCP.

Example Usage

User: "What's our policy on remote work?"
→ ask_wiki searches your wiki and returns an answer with source links

User: "Find documents related to the onboarding guide"
→ find_related returns semantically similar docs (not just keyword matches)

User: "Summarize the Q4 planning document"
→ summarize_document generates a concise summary in your preferred language

Supported Clients

ClientToolsResourcesPrompts
Claude Desktop
Claude Code
VS Code GitHub Copilot
Cursor-
Windsurf--
ChatGPT Desktop--

Getting Started

Requirements

  • Node.js 18.0.0 or higher
  • Outline instance with API access
  • (Optional) OpenAI API key for smart features

Getting Your Outline API Token

  1. Log in to your Outline instance
  2. Go to SettingsAPI
  3. Click Create API Key
  4. Copy the generated token (starts with ol_api_)

Installation

Claude Desktop

Add to your Claude Desktop configuration:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "outline": {
      "command": "npx",
      "args": ["-y", "outline-smart-mcp"],
      "env": {
        "OUTLINE_URL": "https://your-outline-instance.com",
        "OUTLINE_API_TOKEN": "ol_api_xxxxxxxxxxxxx"
      }
    }
  }
}
Claude Code

Run the following command:

claude mcp add outline -e OUTLINE_URL=https://your-outline-instance.com -e OUTLINE_API_TOKEN=ol_api_xxxxxxxxxxxxx -- npx -y outline-smart-mcp

Or add to ~/.claude.json (global) or .mcp.json (project-local):

{
  "mcpServers": {
    "outline": {
      "command": "npx",
      "args": ["-y", "outline-smart-mcp"],
      "env": {
        "OUTLINE_URL": "https://your-outline-instance.com",
        "OUTLINE_API_TOKEN": "ol_api_xxxxxxxxxxxxx"
      }
    }
  }
}

Note: The ~/.claude/settings.json file is ignored for MCP servers. Use ~/.claude.json or .mcp.json instead.

VS Code GitHub Copilot

Add to your VS Code settings (.vscode/mcp.json):

{
  "servers": {
    "outline": {
      "command": "npx",
      "args": ["-y", "outline-smart-mcp"],
      "env": {
        "OUTLINE_URL": "https://your-outline-instance.com",
        "OUTLINE_API_TOKEN": "ol_api_xxxxxxxxxxxxx"
      }
    }
  }
}
Cursor

Add to Cursor MCP settings (~/.cursor/mcp.json):

{
  "mcpServers": {
    "outline": {
      "command": "npx",
      "args": ["-y", "outline-smart-mcp"],
      "env": {
        "OUTLINE_URL": "https://your-outline-instance.com",
        "OUTLINE_API_TOKEN": "ol_api_xxxxxxxxxxxxx"
      }
    }
  }
}
Windsurf

Add to Windsurf MCP settings (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "outline": {
      "command": "npx",
      "args": ["-y", "outline-smart-mcp"],
      "env": {
        "OUTLINE_URL": "https://your-outline-instance.com",
        "OUTLINE_API_TOKEN": "ol_api_xxxxxxxxxxxxx"
      }
    }
  }
}
ChatGPT Desktop

ChatGPT supports MCP through its desktop app. Add the server in SettingsMCP Servers with:

  • Command: npx
  • Arguments: -y outline-smart-mcp
  • Environment variables as shown above

Configuration

Environment Variables

VariableDescriptionRequiredDefault
OUTLINE_URLYour Outline instance URLYeshttps://app.getoutline.com
OUTLINE_API_TOKENYour Outline API tokenYes-
READ_ONLYEnable read-only modeNofalse
DISABLE_DELETEDisable delete operationsNofalse
MAX_RETRIESAPI retry attemptsNo3
RETRY_DELAY_MSRetry delay (ms)No1000
ENABLE_SMART_FEATURESEnable AI featuresNofalse
OPENAI_API_KEYOpenAI API keyNo*-

* Required when ENABLE_SMART_FEATURES=true

Smart Features Configuration

To enable AI-powered features (RAG Q&A, summarization, etc.), add these to your config:

{
  "mcpServers": {
    "outline": {
      "command": "npx",
      "args": ["-y", "outline-smart-mcp"],
      "env": {
        "OUTLINE_URL": "https://your-outline-instance.com",
        "OUTLINE_API_TOKEN": "ol_api_xxxxxxxxxxxxx",
        "ENABLE_SMART_FEATURES": "true",
        "OPENAI_API_KEY": "sk-xxxxxxxxxxxxx"
      }
    }
  }
}

Tools

Search & Discovery

ToolDescription
search_documentsSearch documents by keyword with pagination
get_document_id_from_titleFind document ID by title
list_collectionsGet all collections
get_collection_structureGet document hierarchy in a collection
list_recent_documentsGet recently modified documents

Document Operations

ToolDescription
get_documentGet full document content by ID
export_documentExport document in Markdown
create_documentCreate a new document
update_documentUpdate document (supports append)
move_documentMove document to another location

Document Lifecycle

ToolDescription
archive_documentArchive a document
unarchive_documentRestore archived document
delete_documentDelete document (soft/permanent)
restore_documentRestore from trash
list_archived_documentsList archived documents
list_trashList trashed documents

Comments & Collaboration

ToolDescription
add_commentAdd comment (supports replies)
list_document_commentsGet document comments
get_commentGet specific comment
get_document_backlinksFind linking documents

Collection Management

ToolDescription
create_collectionCreate collection
update_collectionUpdate collection
delete_collectionDelete collection
export_collectionExport collection
export_all_collectionsExport all collections

Batch Operations

ToolDescription
batch_create_documentsCreate multiple documents
batch_update_documentsUpdate multiple documents
batch_move_documentsMove multiple documents
batch_archive_documentsArchive multiple documents
batch_delete_documentsDelete multiple documents

Smart Features (AI-Powered)

Requires ENABLE_SMART_FEATURES=true and OPENAI_API_KEY.

ToolDescription
smart_statusCheck status and indexed count
sync_knowledgeSync docs to vector database
ask_wikiRAG-based Q&A on wiki content
summarize_documentGenerate AI summary
suggest_tagsAI-suggested tags
find_relatedFind semantically related docs
generate_diagramGenerate Mermaid diagrams

Smart Features Usage

# 1. First, sync your wiki documents
sync_knowledge

# 2. Ask questions about your wiki
ask_wiki: "What is our deployment process?"

# 3. Summarize long documents
summarize_document: { documentId: "doc-id", language: "Korean" }

# 4. Find related content
find_related: { documentId: "doc-id", limit: 5 }

Technology Stack

ComponentTechnology
Vector DatabaseLanceDB (embedded)
EmbeddingsOpenAI text-embedding-3-small
LLMGPT-4o-mini
Text ChunkingLangChain

Safety Features

Read-Only Mode

READ_ONLY=true

Restricts to read operations only: search, get, export, list operations, and all smart features.

Disable Delete

DISABLE_DELETE=true

Blocks: delete_document, delete_collection, batch_delete_documents

Development

# Clone repository
git clone https://github.com/huiseo/outline-wiki-mcp.git
cd outline-wiki-mcp

# Install dependencies
npm install

# Build
npm run build

# Run tests
npm test

# Type check
npm run typecheck

License

MIT License - see LICENSE for details.

Links

Reviews

No reviews yet

Sign in to write a review