outline-mcp-server
Integrates Outline Wiki with AI assistants like Claude Desktop, enabling search, create, update documents, list collections, and more.
README
Outline MCP Server
A Model Context Protocol (MCP) server that integrates Outline Wiki with AI assistants like Claude Desktop.
Features
- 🔍 Search documents - Find documents in your Outline knowledge base
- 📝 Create documents - Create new documents in any collection
- ✏️ Update documents - Update existing documents (with append support)
- 📁 List collections - View all accessible collections
- 📚 Resources - Access document content and search results as resources
- 💡 Prompts - Pre-configured prompts for document analysis and content creation
Setup
-
Install dependencies:
cd outline-mcp-server python -m venv .venv source .venv/bin/activate pip install -r requirements.txt -
Configure environment: Create a
.envfile with your Outline API token:OUTLINE_TOKEN=your_api_token_here OUTLINE_BASE_URL=https://your-outline-instance.com/api -
Test the server:
python test_server.py
Claude Desktop Integration
The server has been configured in ~/.config/claude-desktop/claude.json.
To use it:
- Restart Claude Desktop
- The Outline tools should appear in the tools menu
- Try commands like:
- "Search for documentation about [topic]"
- "List all collections in Outline"
- "Create a new document about [topic] in [collection]"
Available Tools
search_documents
Search for documents in Outline.
query: Search querylimit: Maximum results (default: 10)
create_document
Create a new document.
title: Document titlecontent: Document content (Markdown)collection_id: Target collection ID
update_document
Update an existing document.
doc_id: Document IDcontent: New contentappend: Append to existing content (default: false)
list_collections
List all accessible collections.
Resources
outline://document/{doc_id}- Get full document contentoutline://search/{query}- Get search results as JSON
Prompts
analyze_document- Analyze a document with various analysis typescreate_overview- Create a topic overview from related documents
Development
The server consists of:
server.py- Main MCP server implementationoutline_client.py- Outline API clienttools.py- Tool implementationsresources.py- Resource handlersprompts.py- Prompt templatestest_server.py- Test script
Troubleshooting
- Server won't start: Check that
OUTLINE_TOKENis set in.env - Connection errors: Verify
OUTLINE_BASE_URLis correct - Claude Desktop doesn't show tools: Restart Claude Desktop after config changes
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.