Redmine MCP Server

Redmine MCP Server

Enables AI applications to interact with Redmine project management systems for issue tracking, time logging, and project management through natural language.

Category
访问服务器

README

Redmine MCP Server

Tests CI

A Model Context Protocol (MCP) server for integrating with Redmine project management systems. This server provides AI applications with the ability to interact with Redmine instances for project management, issue tracking, and time logging.

Features

Tools

  • get_issues - Retrieve issues with optional filtering by project, status, assignee
  • get_projects - List available Redmine projects
  • get_project_memberships - Get users and groups assigned to a project with their roles
  • create_issue - Create new issues in Redmine projects
  • get_time_entries - Retrieve time entries with filtering options
  • log_time - Log time spent on issues or projects

Resources

  • redmine://projects - List of all accessible projects
  • redmine://issues/recent - Recently updated issues
  • redmine://time_entries/recent - Recently logged time entries

Prompts

  • issue_summary - Generate comprehensive project issue summaries
  • time_report - Create detailed time tracking reports

Setup

Prerequisites

  • Node.js 22+
  • Access to a Redmine instance with API key
  • Redmine REST API enabled

Environment Variables

Set the following environment variables:

export REDMINE_URL="https://your-redmine-instance.com"
export REDMINE_API_KEY="your_api_key_here"

Installation

  1. Clone or download this repository
  2. Install dependencies:
    npm install
    
  3. Build the server:
    npm run build
    

Usage with MCP Clients

VsCode

Clone this repository and create the file .vscode/mcp.json with following contents:

{
  "servers": {
    "redmine-mcp-server": {
      "type": "stdio",
      "command": "node",
      "args": ["build/src/index.js"],
      "env": {
        "REDMINE_URL": "your URL here",
        "REDMINE_API_KEY": "your API key here"
      }
    }
  }
}

After adding the file, restart VsCode and open the Chat window. Redmine MCP Server should be available and running in MCP servers list (Ctrl-P, then type "MCP list servers"):

LLM tools view with Redmine MCP visible

Documentation

API documentation is automatically generated from JSDoc comments and deployed to GitHub Pages:

📚 View API Documentation

To generate documentation locally:

npm run docs

The generated documentation will be available in the docs/ directory.

Development

Building

npm run build

Linting

npm run lint
npm run format

Testing

This project uses Vitest as its testing framework, providing fast test execution, watch mode, and comprehensive coverage reports.

Running Tests

# Run all tests
npm test

# Run tests once and exit
npm run test:run

# Run only e2e tests
npm run test:e2e

# Run tests with UI
npm run test:ui

# Run tests with coverage
npm run test:coverage

Coverage Reporting

Code coverage is automatically collected and reported in the CI pipeline using Vitest's built-in coverage support with the V8 provider. Coverage reports are:

  • Generated for every test run in CI
  • Uploaded as workflow artifacts (available for 30 days)
  • Displayed in the GitHub Actions workflow summary
  • Stored in the coverage/ directory locally

To generate coverage locally:

npm run test:coverage

Coverage reports include:

  • HTML report: Open coverage/index.html in your browser for detailed line-by-line coverage
  • JSON summary: coverage/coverage-summary.json contains overall metrics
  • Text output: Coverage percentages displayed in the terminal

The coverage configuration excludes test files, configuration files, and build artifacts to focus on source code coverage.

Test Structure

  • test/e2e/ - End-to-end tests using Docker and Playwright

Writing Tests

Tests use Vitest's describe, it, and expect API:

import { describe, it, expect } from "vitest";

describe("My Feature", () => {
  it("should work correctly", () => {
    expect(1 + 1).toBe(2);
  });
});

Testing with MCP Inspector

npx @modelcontextprotocol/inspector node build/src/index.js

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