
Confluence MCP Server
A Model Context Protocol server that provides secure access to Atlassian Confluence, allowing users to search, create, update, and manage Confluence pages and spaces through natural language commands.
README
Confluence MCP Server
A Model Context Protocol (MCP) server that provides secure access to Atlassian Confluence through its REST API.
Using with Claude Code
To use this MCP server with Claude Code, add it to your MCP configuration file:
Option 1: Using the built version (recommended)
-
First, build the server:
npm run build
-
Add to your MCP configuration file (
~/.config/claude-code/mcp_servers_config.json
):{ "mcpServers": { "confluence": { "command": "node", "args": ["/path/to/confluence_mcp/dist/index.js"], "env": { "CONFLUENCE_BASE_URL": "https://your-domain.atlassian.net", "CONFLUENCE_USERNAME": "your-email@domain.com", "CONFLUENCE_API_TOKEN": "your-api-token", "ALLOWED_SPACES": "SPACE1,SPACE2,SPACE3" } } } }
Option 2: Using tsx for development
For development or if you prefer running TypeScript directly:
{
"mcpServers": {
"confluence": {
"command": "npx",
"args": ["tsx", "/path/to/confluence_mcp/src/index.ts"],
"env": {
"CONFLUENCE_BASE_URL": "https://your-domain.atlassian.net",
"CONFLUENCE_USERNAME": "your-email@domain.com",
"CONFLUENCE_API_TOKEN": "your-api-token",
"ALLOWED_SPACES": "SPACE1,SPACE2,SPACE3"
}
}
}
}
Configuration Notes
- Replace the environment variables with your actual Confluence credentials
- The
ALLOWED_SPACES
should be a comma-separated list of space keys you want to allow access to - Restart Claude Code after updating the configuration
- Make sure you have built the project first with
npm run build
if using Option 1
Once configured, you can use commands like:
- "Search for API documentation in Confluence"
- "Create a new page in the DEV space"
- "Show me all pages in the PROJ space"
Quick Start
-
Install dependencies:
npm install
-
Configure environment:
cp .env.example .env # Edit .env with your Confluence credentials
-
Build and run:
npm run build npm start
Or for development:
npm run dev
Configuration
Create a .env
file with your Confluence credentials:
CONFLUENCE_BASE_URL=https://your-domain.atlassian.net
CONFLUENCE_USERNAME=your-email@domain.com
CONFLUENCE_API_TOKEN=your-api-token
ALLOWED_SPACES=SPACE1,SPACE2,SPACE3
DEBUG=false
Getting an API Token
- Go to Atlassian Account Settings
- Click "Create API token"
- Give it a descriptive label
- Copy the generated token (save it securely!)
Available Tools
- search_confluence - Search content across allowed spaces
- get_page - Retrieve a specific page by ID
- create_page - Create a new page
- update_page - Update an existing page
- delete_page - Delete a page
- list_spaces - List accessible spaces
- get_space_content - Get pages from a specific space
Security Features
- API Token Authentication - Secure access using Atlassian API tokens
- Space Restrictions - Configurable allowed spaces list
- Permission Validation - Respects Confluence permissions
- Request Validation - Input validation and sanitization
Development
# Type checking
npm run typecheck
# Linting
npm run lint
# Testing
npm test
# Build
npm run build
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。
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。
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。

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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。