confluence-mcp-server

lczc1988/confluence-mcp-server

3.1

If you are the rightful owner of confluence-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

A comprehensive Model Context Protocol (MCP) server that integrates with Confluence and Splunk for documentation management and log analysis.

Tools
7
Resources
0
Prompts
0

Confluence + Splunk MCP Server

A comprehensive Model Context Protocol (MCP) server that provides integration with both Confluence and Splunk, allowing you to manage documentation, search logs, and monitor systems through GitHub Copilot and other MCP-compatible clients.

🌟 Features

Confluence Integration

  • Page Management: Create, read, update, and delete Confluence pages
  • Space Management: Get space information and list all spaces
  • Content Search: Search for pages using Confluence Query Language (CQL)
  • Full API Integration: Complete integration with Confluence REST API

Splunk Integration ✨ NEW

  • Log Search: Search logs using Splunk Processing Language (SPL)
  • Index Management: List and explore available Splunk indexes
  • Alert Management: Create and manage Splunk alerts/saved searches
  • Real-time Monitoring: Monitor system health and security events
  • Performance Analytics: Analyze application and infrastructure performance
  • 🏢 Ford SSO Support: Specialized integration for Ford's Splunk environment

Server Options

  • Confluence-only server: For pure documentation management
  • Splunk-only server: For pure log analysis and monitoring
  • Ford Splunk server: Optimized for Ford's SSO environment
  • Combined server: Unified access to both Confluence and Splunk (recommended)

🚀 Quick Start

  1. Clone and Install:
git clone <repository-url>
cd confluencemcplocal
npm install
  1. Configure Services:
cp .env.example .env
# Edit .env with your Confluence and/or Splunk credentials
  1. Build and Test:
npm run build

# Test Confluence (if configured)
./interactive-test.sh

# Test Splunk (if configured) 
./splunk-quick-test.sh

# Test Ford Splunk (if using Ford SSO)
./ford-splunk-test.sh

# Run interactive demo
./splunk-demo.sh
  1. Start the Server:
# Combined server (recommended)
npm run start:combined

# Or individual servers
npm run start:confluence
npm run start:splunk
npm run start:ford-splunk  # For Ford SSO environment

⚙️ Configuration

Environment Variables

Create a .env file with your service credentials:

# Confluence Configuration (optional)
CONFLUENCE_BASE_URL=https://your-domain.atlassian.net
CONFLUENCE_USERNAME=your-email@example.com
CONFLUENCE_API_TOKEN=your-confluence-api-token

# Splunk Configuration (optional)
SPLUNK_BASE_URL=https://your-splunk-instance.com:8089
SPLUNK_USERNAME=your-splunk-username
SPLUNK_PASSWORD=your-splunk-password
SPLUNK_DEFAULT_INDEX=main

# Ford Splunk SSO Configuration (for Ford environments)
SPLUNK_BASE_URL=https://ford-splunk-instance.ford.com:8089
SPLUNK_AUTH_METHOD=token  # or 'basic', 'session'
SPLUNK_API_TOKEN=your-ford-splunk-api-token
SPLUNK_DEFAULT_INDEX=main

Getting API Credentials

Confluence API Token
  1. Go to Atlassian API tokens
  2. Click "Create API token"
  3. Give it a label and copy the generated token
  4. Use your email as the username
Splunk Credentials
  1. Use your existing Splunk username and password
  2. Ensure your user has search permissions for the indexes you want to query
  3. For production use, consider creating a dedicated service account

🔧 Usage

Available Scripts

# Build the project
npm run build

# Start individual servers
npm run start:confluence    # Confluence only
npm run start:splunk       # Splunk only  
npm run start:combined     # Both services (recommended)

# Development mode with auto-rebuild
npm run dev

# Testing scripts
./interactive-test.sh       # Test Confluence integration
./splunk-quick-test.sh     # Quick Splunk connectivity test
./splunk-interactive-test.sh # Interactive Splunk testing
./splunk-demo.sh           # Comprehensive demo scenarios

Testing Your Setup

  1. Quick connectivity test:
./splunk-quick-test.sh
  1. Interactive testing:
./splunk-interactive-test.sh
  1. Full demo with real-world scenarios:
./splunk-demo.sh

{
  "servers": {
    "confluence-mcp": {
      "type": "stdio",
      "command": "node",
      "args": ["/Users/chao/Documents/workspace/confluencemcp/dist/index.js"],
      "env": {
        "CONFLUENCE_BASE_URL": "https://your-domain.atlassian.net",
        "CONFLUENCE_USERNAME": "your-email@example.com", 
        "CONFLUENCE_API_TOKEN": "your-api-token"
      }
    }
  }
}

  1. 重启VS Code，MCP server将自动可用于GitHub Copilot。

  2. 现在你可以在Copilot Chat中使用Confluence相关的命令！

🚀 GitHub Copilot 使用指南

基础语法
@mcp [操作] [参数]
常用命令示例
# 列出所有Confluence空间
@mcp list spaces

# 搜索页面
@mcp search "Authorization"

# 在特定空间中搜索
@mcp search "API" in space:CDL

# 获取页面详情
@mcp get page:607043116

# 创建新页面
@mcp create page in space:CDL title:"新文档" content:"内容"
🎯 实际使用示例
用户: @mcp search "authorization" in space:CDL
Copilot: 在 Chinese Dev Lab 空间中找到 3 个关于授权的页面：
1. 1.3.1 Authorization - 用户授权流程详细说明
2. 1.3 Auth/De-auth - 授权和去授权流程  
3. Authorization Overview - 授权概览文档

📚 详细使用指南: 查看 GITHUB_COPILOT_MCP_GUIDE.md 获取完整的命令参考 📋 快速参考: 查看 MCP_QUICK_REFERENCE.md 获取常用命令

验证安装

运行快速测试脚本：

./quick-test.sh

或手动测试：

echo '{}' | node dist/index.js

你应该看到输出："Confluence MCP server running on stdio"

Available Tools

get_page

Retrieve a Confluence page by its ID.

Parameters:

  • pageId (string): The ID of the page to retrieve
  • expand (string, optional): Comma-separated list of properties to expand

search_pages

Search for Confluence pages using CQL.

Parameters:

  • cql (string): Confluence Query Language query string
  • limit (number, optional): Maximum number of results (default: 10)

Example CQL queries:

  • text ~ "keyword" - Search for pages containing a keyword
  • space = "SPACE_KEY" - Find pages in a specific space
  • title ~ "title*" - Search by title pattern

create_page

Create a new Confluence page.

Parameters:

  • spaceKey (string): The key of the space to create the page in
  • title (string): The title of the new page
  • content (string): The content in storage format (HTML)
  • parentId (string, optional): Optional parent page ID

update_page

Update an existing Confluence page.

Parameters:

  • pageId (string): The ID of the page to update
  • title (string): The new title for the page
  • content (string): The new content in storage format (HTML)
  • versionNumber (number): The current version number of the page

delete_page

Delete a Confluence page.

Parameters:

  • pageId (string): The ID of the page to delete

get_space

Get information about a Confluence space.

Parameters:

  • spaceKey (string): The key of the space to retrieve
  • expand (string, optional): Comma-separated list of properties to expand

list_spaces

List all Confluence spaces.

Parameters:

  • limit (number, optional): Maximum number of spaces to return (default: 10)
  • start (number, optional): Starting index for pagination (default: 0)

Development

# Watch mode for development
npm run dev

# Build the project
npm run build

# Run the built project
npm start

Error Handling

The server includes comprehensive error handling for:

  • Invalid Confluence API credentials
  • Network connectivity issues
  • Invalid page/space IDs
  • Permission errors
  • Malformed requests

All errors are returned as proper MCP error responses with descriptive messages.

Security Notes

  • Never commit API tokens to version control
  • Use environment variables for all sensitive configuration
  • Consider using OAuth 2.0 for production deployments
  • Regularly rotate API tokens

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

License

ISC License - see LICENSE file for details.