MCP Confluence

MCP Confluence

A Model Context Protocol (MCP) server for integrating Confluence with OpenCode. Seamlessly search, read, create, and update Confluence pages directly from your AI coding agent.

Category
访问服务器

README

MCP Confluence

A Model Context Protocol (MCP) server for integrating Confluence with OpenCode. Seamlessly search, read, create, and update Confluence pages directly from your AI coding agent.

Features

  • ✅ Search Confluence content by keywords
  • ✅ List available spaces
  • ✅ Get space content
  • ✅ Read Confluence pages by ID
  • ✅ Create new pages
  • ✅ Update existing pages
  • ✅ Full TypeScript support

Requirements

  • Node.js 18+
  • Confluence API credentials (email + API token)

Installation

Using npm

npm install @jsalamanc_01/mcp-confluence

Or use directly with OpenCode

npx @jsalamanc_01/mcp-confluence

Configuration

1. Get Your Confluence API Token

  1. Go to https://id.atlassian.com/manage/api-tokens
  2. Create a new API token
  3. Copy the token and save it securely

2. Setup with OpenCode

Add this to your ~/.config/opencode/opencode.jsonc:

{
  "mcp": {
    "confluence": {
      "type": "local",
      "command": ["npx", "-y", "@jsalamanc_01/mcp-confluence"],
      "enabled": true,
      "environment": {
        "CONFLUENCE_BASE_URL": "https://your-instance.atlassian.net",
        "CONFLUENCE_EMAIL": "your-email@example.com",
        "CONFLUENCE_API_TOKEN": "your-api-token-here"
      }
    }
  }
}

Or use environment variables:

{
  "mcp": {
    "confluence": {
      "type": "local",
      "command": ["npx", "-y", "@jsalamanc_01/mcp-confluence"],
      "enabled": true,
      "environment": {
        "CONFLUENCE_BASE_URL": "{env:CONFLUENCE_BASE_URL}",
        "CONFLUENCE_EMAIL": "{env:CONFLUENCE_EMAIL}",
        "CONFLUENCE_API_TOKEN": "{env:CONFLUENCE_API_TOKEN}"
      }
    }
  }
}

Usage

Once configured, you can use Confluence tools with OpenCode:

Search for all pages about "API" in Confluence. use confluence

Available Tools

Search Tools (3)

  • search_confluence - Search Confluence content by keywords

    • Parameters: query (string), limit (number, default: 25)
    • Returns: List of matching pages with metadata
  • get_confluence_spaces - List all available spaces

    • Parameters: limit (number, default: 25)
    • Returns: List of all Confluence spaces
  • get_space_content - Get all pages in a space

    • Parameters: space_key (string), limit (number, default: 25)
    • Returns: List of pages in the specified space

Page Management Tools (6)

  • get_confluence_page - Read a page by ID

    • Parameters: page_id (string)
    • Returns: Full page content with metadata
  • create_confluence_page - Create a new page

    • Parameters: space_key (string), title (string), body (string), parent_page_id (optional)
    • Returns: Created page details with URL
  • update_confluence_page - Update an existing page

    • Parameters: page_id (string), title (string), body (string), version_number (number)
    • Returns: Updated page details
  • delete_confluence_page - Delete a page permanently

    • Parameters: page_id (string)
    • Returns: Success confirmation

Collaboration Tools (3)

  • add_confluence_comment - Add a comment to a page

    • Parameters: page_id (string), comment_text (string)
    • Returns: Comment confirmation with details
  • get_confluence_page_comments - Get all comments on a page

    • Parameters: page_id (string), limit (number, default: 25)
    • Returns: List of all comments with author and timestamp
  • get_confluence_page_versions - Get version history

    • Parameters: page_id (string), limit (number, default: 25)
    • Returns: List of all versions with editor info

Attachments & Export Tools (2)

  • get_confluence_page_attachments - List page attachments

    • Parameters: page_id (string), limit (number, default: 25)
    • Returns: List of files attached to the page
  • export_confluence_page_html - Export page as HTML

    • Parameters: page_id (string)
    • Returns: HTML content of the page

Total: 14 tools

Examples

Search for pages

Find all documentation about database migrations using confluence

Create a page

Create a new page in the PROJ space titled "API Documentation" with installation instructions. use confluence

Update a page

Update the README page with the latest changes. use confluence

Delete a page

Delete the old migration guide page. use confluence

Add a comment

Add a comment to the API documentation page saying "Updated with v2 endpoints". use confluence

View page history

Show me the version history of the API documentation page. use confluence

Get all comments

Get all comments on the deployment guide page. use confluence

Export a page

Export the API documentation page as HTML. use confluence

Development

Local Setup

git clone https://github.com/jsalamanc/mcp-confluence.git
cd mcp-confluence
npm install
npm run build

Commands

# Watch for changes
npm run watch

# Run in development mode
npm run dev

# Build for production
npm run build

# Start the server
npm start

Project Structure

src/
├── index.ts                 # Entry point
├── server.ts               # MCP server implementation
├── confluence-client.ts    # Confluence API client with all methods
├── types.ts                # TypeScript types
└── tools/
    ├── page-tools.ts       # Page operations (read, create, update)
    ├── search-tools.ts     # Search operations
    └── advanced-tools.ts   # Advanced tools (delete, comments, versions, etc)

API Reference

The tools use the Confluence Cloud REST API v2.

Authentication

All requests are authenticated using HTTP Basic Auth with:

  • Username: Your Confluence email
  • Password: Your API token

Content Format

Page content uses Confluence's Storage Format (HTML-based markup):

<p>This is a paragraph</p>
<h1>This is a heading</h1>
<ul>
  <li>List item</li>
</ul>

Environment Variables

  • CONFLUENCE_BASE_URL (required): Your Confluence instance URL (e.g., https://my-company.atlassian.net)
  • CONFLUENCE_EMAIL (required): Your Confluence email address
  • CONFLUENCE_API_TOKEN (required): Your Confluence API token

Troubleshooting

Authentication Error

  • Verify your email and API token are correct
  • Ensure the API token hasn't expired
  • Check that the base URL doesn't have a trailing slash

Page Not Found

  • Verify the page ID is correct
  • Ensure you have access to the page
  • Check that the page exists and hasn't been deleted

Publishing Error

  • Verify the space key is correct
  • Ensure you have write permissions to the space
  • Check the HTML format of the body content

Performance

  • Search operations are cached for 5 minutes
  • Batch operations are limited to 25 items by default
  • API calls have a 30-second timeout

Security

  • Never commit your API tokens or credentials
  • Use environment variables for sensitive data
  • Regenerate tokens if they're exposed
  • Restrict API token permissions to minimum required

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Roadmap

✅ Completed (v0.3.0)

  • [x] Search pages
  • [x] List spaces
  • [x] Get space content
  • [x] Read pages
  • [x] Create pages
  • [x] Update pages
  • [x] Delete pages
  • [x] Add comments
  • [x] Get page comments
  • [x] Get page versions/history
  • [x] List page attachments
  • [x] Export pages as HTML

🚀 Planned Features

  • [ ] Upload attachments to pages
  • [ ] Export pages to PDF
  • [ ] Manage page permissions
  • [ ] Work with page macros
  • [ ] Batch operations
  • [ ] Watch/subscribe to page changes
  • [ ] Move pages between spaces
  • [ ] Archive/restore pages

License

MIT

Support

For issues, questions, or suggestions:

Related Projects


Made with ❤️ for the OpenCode community

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选