Changerawr MCP Server

Changerawr MCP Server

A Model Context Protocol server that enables AI assistants like Claude to manage changelogs, projects, and content through natural language interactions with Changerawr instances.

Category
访问服务器

README

Changerawr MCP Server

A Model Context Protocol (MCP) server for Changerawr, enabling AI assistants like Claude to manage changelogs, projects, and content through natural language.

Features

🚀 Project Management

  • List, create, update, and delete projects
  • Configure project settings (public visibility, auto-publish, approval requirements)

📝 Changelog Management

  • Create, update, publish, and unpublish changelog entries
  • Support for versioning and tagging
  • Markdown content with rich formatting

🏷️ Tag Organization

  • Create and manage tags for organizing entries
  • Project-specific tag management

📊 Analytics & Insights

  • Get dashboard statistics and analytics
  • Track project information

🔧 Project Settings

  • Update project configuration
  • Manage default tags and publishing settings

Installation & Setup

Prerequisites

  • Node.js 18+ installed
  • Access to a Changerawr instance
  • An admin API key from Changerawr

1. Clone the Repository

git clone <repository-url>
cd changerawr-mcp-server

2. Install Dependencies

npm install

3. Get Your Changerawr API Key

  1. Log in to your Changerawr admin panel
  2. Navigate to Settings → API Keys
  3. Create a new API key with admin permissions
  4. Copy the key (format: chr_...)

4. Configure Claude Desktop

Add this configuration to your Claude Desktop config.json:

Windows Location: %APPDATA%\Claude\config.json macOS Location: ~/Library/Application Support/Claude/config.json

{
  "mcpServers": {
    "changerawr": {
      "command": "npx",
      "args": ["tsx", "C:\\Users\\username\\WebstormProjects\\changerawr-mcp-server\\src\\index.ts"],
      "env": {
        "CHANGERAWR_API_KEY": "chr_your_api_key_here",
        "CHANGERAWR_BASE_URL": "https://your-changerawr-domain.com",
        "NODE_ENV": "development"
      }
    }
  }
}

Important: Replace the path with your actual project location and update the environment variables:

  • CHANGERAWR_API_KEY: Your actual API key from Changerawr
  • CHANGERAWR_BASE_URL: Your Changerawr instance URL

5. Restart Claude Desktop

Close Claude Desktop completely and restart it for the configuration to take effect.

Usage Examples

Project Management

Create a new project:

"Create a new project called 'Mobile App' with auto-publish enabled and make it public"

List all projects:

"Show me all my projects in Changerawr"

Update project settings:

"Make the Mobile App project private and require approval for all changes"

Changelog Management

Create a draft changelog entry:

"Create a changelog entry for version 2.1.0 titled 'Enhanced Search Features' with details about the new search functionality"

Create and publish immediately:

"Create and immediately publish a changelog entry for version 2.1.1 about bug fixes"

Publish a draft:

"Show me unpublished changelog entries and publish the one about enhanced security"

Update an existing entry:

"Update the changelog entry with ID xyz to include information about performance improvements"

Tag Management

List tags for a project:

"Show me all tags available for the Mobile App project"

Create a new tag:

"Create a new tag called 'Security Update' for the Mobile App project"

Analytics

Get dashboard statistics:

"Show me the dashboard statistics and recent activity"

Available Tools

The MCP server provides 22 tools for comprehensive Changerawr management:

Project Tools (5)

  • list_projects - List all projects
  • get_project - Get project details
  • create_project - Create new project
  • update_project - Update project settings
  • delete_project - Delete project (admin)

Changelog Tools (8)

  • list_changelog_entries - List changelog entries with filtering
  • get_changelog_entry - Get specific entry details
  • create_changelog_entry - Create new draft entry
  • update_changelog_entry - Update existing entry
  • publish_changelog_entry - Publish entry to make it public
  • unpublish_changelog_entry - Hide entry from public
  • delete_changelog_entry - Delete entry permanently (admin)
  • create_and_publish_changelog_entry - Create and publish in one step

Tag Tools (3)

  • list_tags - List tags for a project
  • create_tag - Create new project tag
  • delete_tag - Delete tag (limited API support)

Settings Tools (2)

  • get_project_settings - Get project configuration
  • update_project_settings - Update project settings

Analytics Tools (1)

  • get_dashboard_stats - Get dashboard statistics

Resources (3)

  • changerawr://projects - List of all projects
  • changerawr://projects/{projectId}/changelog - Project changelog entries
  • changerawr://tags - Available tags

Workflows

Draft → Review → Publish (Recommended)

  1. Create Draft: create_changelog_entry - Creates unpublished entry
  2. Review Content: Edit and review the content
  3. Publish: publish_changelog_entry - Makes it visible to users

Immediate Publishing

  1. Create & Publish: create_and_publish_changelog_entry - One-step process

Admin Permissions

All API keys have admin access, enabling:

  • Instant project creation/deletion
  • Immediate publish/unpublish
  • Direct entry deletion
  • Full project settings control
  • Tag management

Troubleshooting

Connection Issues

  1. Verify API key: Ensure it starts with chr_ and has admin permissions
  2. Check URL: Verify your Changerawr instance URL is correct
  3. Test connection: Try accessing your Changerawr instance in a browser

Claude Desktop Issues

  1. Check logs: Windows: %APPDATA%\Claude\logs\
  2. Restart completely: Close Claude Desktop from system tray
  3. Verify config path: Ensure the file path in config.json is correct

Tool Failures

  1. Check stderr output: The MCP server logs detailed error information
  2. Verify project IDs: Ensure you're using correct project/entry IDs
  3. API permissions: Confirm your API key has admin access

Development

Run in Development Mode

cd changerawr-mcp-server
npx tsx src/index.ts

Testing Tools

Use the MCP Inspector for testing:

npx @modelcontextprotocol/inspector npx tsx src/index.ts

Environment Variables

Variable Required Description
CHANGERAWR_API_KEY Your Changerawr API key (starts with chr_)
CHANGERAWR_BASE_URL Your Changerawr instance URL
NODE_ENV Set to development for detailed logging

Architecture

src/
├── index.ts              # Main MCP server entry point
├── client/
│   └── changerawr-client.ts  # API client with Zod validation
├── tools/                # MCP tools for AI interactions
│   ├── index.ts          # Tool registry
│   ├── project-tools.ts  # Project management (5 tools)
│   ├── changelog-tools.ts # Changelog operations (8 tools)
│   ├── tag-tools.ts      # Tag management (3 tools)
│   ├── settings-tools.ts # Project settings (2 tools)
│   └── analytics-tools.ts # Dashboard analytics (1 tool)
├── resources/            # MCP resources for data access
│   ├── index.ts          # Resource registry
│   ├── project-resources.ts
│   └── changelog-resources.ts
└── utils/
    └── validation.ts     # Input validation utilities

Security

  • Uses Changerawr's existing API key authentication
  • Respects admin permissions and role-based access
  • All operations logged via Changerawr's audit system
  • Input validation and error handling for safe operations

License

MIT License - see LICENSE file for details

Support

For issues and questions:

  • Check the troubleshooting section above
  • Review Claude Desktop logs for detailed error information
  • Ensure your Changerawr instance is accessible and API key is valid

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