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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。