Redmine MCP Server
Enables AI assistants to interact with Redmine instances to manage issues, projects, and users. It provides comprehensive tools for issue tracking, project oversight, and user management through the Redmine REST API.
README
Redmine MCP Server
A Model Context Protocol (MCP) server for Redmine integration, built with TypeScript following TDD methodology. This server allows AI assistants to interact with Redmine instances to manage issues, projects, and users with comprehensive security and monitoring features.
Features
- Issue Management: Create, read, update, and list issues
- Project Management: List and view project details
- User Management: List and view user information
- Error Handling: Comprehensive error handling with meaningful error messages
- Type Safety: Full TypeScript implementation with proper type definitions
Installation
npm install
npm run build
Configuration
The server requires two environment variables:
REDMINE_BASE_URL: The base URL of your Redmine instance (e.g.,https://redmine.example.com)REDMINE_API_KEY: Your Redmine API key (found in your account settings)
Usage
Running the Server
export REDMINE_BASE_URL="https://your-redmine-instance.com"
export REDMINE_API_KEY="your-api-key-here"
npm run dev
Building and Running
npm run build
export REDMINE_BASE_URL="https://your-redmine-instance.com"
export REDMINE_API_KEY="your-api-key-here"
npm start
Production Deployment
# Build the project
npm run build
# Set production environment variables
export REDMINE_BASE_URL="https://your-redmine-instance.com"
export REDMINE_API_KEY="your-api-key-here"
export LOG_LEVEL="info"
# Start the server
npm start
Available Tools
Issue Tools
-
list-issues: List issues with optional filtering
- Parameters:
project_id,status_id,assigned_to_id,limit,offset
- Parameters:
-
create-issue: Create a new issue
- Required:
project_id,subject - Optional:
description,tracker_id,status_id,priority_id,assigned_to_id
- Required:
-
get-issue: Get details of a specific issue
- Required:
id
- Required:
-
update-issue: Update an existing issue
- Required:
id - Optional:
subject,description,status_id,priority_id,assigned_to_id,done_ratio
- Required:
Project Tools
-
list-projects: List all projects
-
get-project: Get details of a specific project
- Required:
id(can be numeric ID or string identifier)
- Required:
User Tools
-
list-users: List all users
-
get-user: Get details of a specific user
- Required:
id
- Required:
Development
Running Tests
npm test
Running Tests with Coverage
npm run test:coverage
Running in Watch Mode
npm run test:watch
Linting
npm run lint
Type Checking
npm run typecheck
Clean Build Directory
npm run clean
API Reference
RedmineClient
The core client for interacting with Redmine's REST API.
const client = new RedmineClient({
baseUrl: 'https://redmine.example.com',
apiKey: 'your-api-key'
});
RedmineMcpServer
The MCP server that exposes Redmine functionality as MCP tools.
const server = new RedmineMcpServer({
baseUrl: 'https://redmine.example.com',
apiKey: 'your-api-key'
});
await server.start();
Error Handling
The server provides comprehensive error handling for common scenarios:
- Authentication errors (401): Invalid API key
- Authorization errors (403): Insufficient permissions
- Not found errors (404): Resource doesn't exist
- Validation errors (422): Invalid data provided
- Server errors (500): Internal server issues
- Network errors: Connection timeouts and network issues
- Input validation: Client-side validation with detailed error messages
Logging
The server includes structured logging with configurable levels:
- DEBUG: Detailed execution information and request/response data
- INFO: General operational information (default)
- WARN: Warning conditions that don't affect operation
- ERROR: Error conditions that require attention
Configure the log level using the LOG_LEVEL environment variable:
export LOG_LEVEL="debug" # For development
export LOG_LEVEL="info" # For production (default)
export LOG_LEVEL="error" # For minimal logging
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Run the test suite
- Submit a pull request
License
MIT License
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。