Redmine MCP Server
An MCP server that connects AI assistants to Redmine, enabling issue and project management via natural language.
README
Redmine MCP Server
An MCP (Model Context Protocol) server that connects AI assistants like Kiro to your Redmine instance. It exposes 15 tools covering Issues, Projects, and Search — allowing your AI assistant to create issues, update projects, search across resources, and more, all through natural conversation.
What it does
Once configured, you can ask your AI assistant things like:
- "List all open issues assigned to me"
- "Create a bug report for the login page crash"
- "Search for issues related to database migration"
- "Archive the old-website project"
- "Add John as a watcher on issue #42"
The server handles authentication, pagination, input validation, and error handling automatically.
Available tools
| Domain | Tools |
|---|---|
| Issues | list, get, create, update, delete, add watcher, remove watcher |
| Projects | list, get, create, update, delete, archive, unarchive |
| Search | full-text search across all Redmine resources |
Prerequisites
- Python 3.10+ installed on your machine
- uv — a fast Python package manager (install guide)
- macOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh - Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
- macOS/Linux:
- Redmine API key — get yours from your Redmine instance:
- Log in to Redmine
- Go to My Account (top-right menu)
- In the right sidebar, find API access key and click Show
- Copy the key
Setup with Kiro
Step 1: Add the MCP server config to Kiro
Create or edit ~/.kiro/settings/mcp.json (this makes it available across all your projects):
{
"mcpServers": {
"redmine": {
"command": "uvx",
"args": ["--from", "git+https://github.com/suryamalempati/redmine-mcp-server.git", "redmine-mcp-server"],
"env": {
"REDMINE_URL": "https://your-redmine-instance.com",
"REDMINE_API_KEY": "your-api-key-here"
},
"disabled": false
}
}
}
Replace:
https://your-redmine-instance.comwith your Redmine URLyour-api-key-herewith your Redmine API key
You can also place this in .kiro/settings/mcp.json within a specific workspace if you only want it available there.
Step 2: Open Kiro
The MCP server will start automatically when Kiro launches. You can verify it's working by asking: "List my Redmine projects."
Alternative setup: Local install
If you prefer to run from a local clone instead of uvx:
git clone https://github.com/suryamalempati/redmine-mcp-server.git
cd redmine-mcp-server
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install .
Then use this MCP config instead:
{
"mcpServers": {
"redmine": {
"command": "/absolute/path/to/redmine-mcp/.venv/bin/redmine-mcp-server",
"args": [],
"env": {
"REDMINE_URL": "https://your-redmine-instance.com",
"REDMINE_API_KEY": "your-api-key-here"
},
"disabled": false
}
}
}
Troubleshooting
| Problem | Solution |
|---|---|
| "REDMINE_URL environment variable is missing" | Make sure REDMINE_URL is set in the MCP config's env block |
| "REDMINE_API_KEY environment variable is missing" | Ensure REDMINE_API_KEY is set in the MCP config's env block |
| "Authentication failed: invalid or expired API key" | Verify your API key is correct in Redmine → My Account → API access key |
| "Connection failed" | Check that the REDMINE_URL is reachable from your machine |
| Tools not appearing in Kiro | Confirm the mcp.json file is in the right location and "disabled" is false |
Development
git clone https://github.com/suryamalempati/redmine-mcp-server.git
cd redmine-mcp-server
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest
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。