Taiga AI桥
连接AI系统与Taiga项目管理平台的协议桥,使AI工具能够创建和管理项目、史诗、用户故事、任务、问题和冲刺。
可用工具 (60 个)
该服务在 MCP 协议中暴露的工具,AI 可按需调用
login 3 个参数 需填 3 项
Logs into a Taiga instance using username/password and returns a session_id for subsequent authenticated calls.
必填参数:host、username、password
list_projects 1 个参数 需填 1 项
Lists projects accessible to the user associated with the provided session_id.
必填参数:session_id
list_all_projects 1 个参数 需填 1 项
Lists all projects visible to the user (requires admin privileges for full list). Uses the provided session_id.
必填参数:session_id
get_project 2 个参数 需填 2 项
Gets detailed information about a specific project by its ID.
必填参数:session_id、project_id
get_project_by_slug 2 个参数 需填 2 项
Gets detailed information about a specific project by its slug.
必填参数:session_id、slug
update_project 3 个参数 需填 3 项
Updates details of an existing project.
必填参数:session_id、project_id、kwargs
delete_project 2 个参数 需填 2 项
Deletes a project by its ID. This is irreversible.
必填参数:session_id、project_id
get_project_roles 2 个参数 需填 2 项
Lists the available roles within a specific project.
必填参数:session_id、project_id
list_user_stories 3 个参数 需填 3 项
Lists user stories within a specific project, optionally filtered.
必填参数:session_id、project_id、filters
create_user_story 4 个参数 需填 4 项
Creates a new user story within a project.
必填参数:session_id、project_id、subject、kwargs
get_user_story 2 个参数 需填 2 项
Gets detailed information about a specific user story by its ID.
必填参数:session_id、user_story_id
get_user_story_by_ref 3 个参数 需填 3 项
Gets detailed information about a specific user story by its reference number within a project.
必填参数:session_id、project_id、ref
update_user_story 3 个参数 需填 3 项
Updates details of an existing user story.
必填参数:session_id、user_story_id、kwargs
delete_user_story 2 个参数 需填 2 项
Deletes a user story by its ID.
必填参数:session_id、user_story_id
assign_user_story_to_user 3 个参数 需填 3 项
Assigns a specific user story to a specific user.
必填参数:session_id、user_story_id、user_id
unassign_user_story_from_user 2 个参数 需填 2 项
Unassigns a specific user story (sets assigned user to null).
必填参数:session_id、user_story_id
get_user_story_statuses 2 个参数 需填 2 项
Lists the available statuses for user stories within a specific project.
必填参数:session_id、project_id
list_tasks 3 个参数 需填 3 项
Lists tasks within a specific project, optionally filtered.
必填参数:session_id、project_id、filters
create_task 4 个参数 需填 4 项
Creates a new task within a project.
必填参数:session_id、project_id、subject、kwargs
get_task 2 个参数 需填 2 项
Gets detailed information about a specific task by its ID.
必填参数:session_id、task_id
get_task_by_ref 3 个参数 需填 3 项
Gets detailed information about a specific task by its reference number within a project.
必填参数:session_id、project_id、ref
update_task 3 个参数 需填 3 项
Updates details of an existing task.
必填参数:session_id、task_id、kwargs
delete_task 2 个参数 需填 2 项
Deletes a task by its ID.
必填参数:session_id、task_id
assign_task_to_user 3 个参数 需填 3 项
Assigns a specific task to a specific user.
必填参数:session_id、task_id、user_id
unassign_task_from_user 2 个参数 需填 2 项
Unassigns a specific task (sets assigned user to null).
必填参数:session_id、task_id
get_task_statuses 2 个参数 需填 2 项
Lists the available statuses for tasks within a specific project.
必填参数:session_id、project_id
list_issues 3 个参数 需填 3 项
Lists issues within a specific project, optionally filtered.
必填参数:session_id、project_id、filters
create_issue 8 个参数 需填 8 项
Creates a new issue within a project.
必填参数:session_id、project_id、subject、priority_id、status_id、severity_id、type_id、kwargs
get_issue 2 个参数 需填 2 项
Gets detailed information about a specific issue by its ID.
必填参数:session_id、issue_id
get_issue_by_ref 3 个参数 需填 3 项
Gets detailed information about a specific issue by its reference number within a project.
必填参数:session_id、project_id、ref
update_issue 3 个参数 需填 3 项
Updates details of an existing issue.
必填参数:session_id、issue_id、kwargs
delete_issue 2 个参数 需填 2 项
Deletes an issue by its ID.
必填参数:session_id、issue_id
assign_issue_to_user 3 个参数 需填 3 项
Assigns a specific issue to a specific user.
必填参数:session_id、issue_id、user_id
unassign_issue_from_user 2 个参数 需填 2 项
Unassigns a specific issue (sets assigned user to null).
必填参数:session_id、issue_id
get_issue_statuses 2 个参数 需填 2 项
Lists the available statuses for issues within a specific project.
必填参数:session_id、project_id
get_issue_priorities 2 个参数 需填 2 项
Lists the available priorities for issues within a specific project.
必填参数:session_id、project_id
get_issue_severities 2 个参数 需填 2 项
Lists the available severities for issues within a specific project.
必填参数:session_id、project_id
get_issue_types 2 个参数 需填 2 项
Lists the available types for issues within a specific project.
必填参数:session_id、project_id
list_epics 3 个参数 需填 3 项
Lists epics within a specific project, optionally filtered.
必填参数:session_id、project_id、filters
create_epic 4 个参数 需填 4 项
Creates a new epic within a project.
必填参数:session_id、project_id、subject、kwargs
get_epic 2 个参数 需填 2 项
Gets detailed information about a specific epic by its ID.
必填参数:session_id、epic_id
get_epic_by_ref 3 个参数 需填 3 项
Gets detailed information about a specific epic by its reference number within a project.
必填参数:session_id、project_id、ref
update_epic 3 个参数 需填 3 项
Updates details of an existing epic.
必填参数:session_id、epic_id、kwargs
delete_epic 2 个参数 需填 2 项
Deletes an epic by its ID.
必填参数:session_id、epic_id
assign_epic_to_user 3 个参数 需填 3 项
Assigns a specific epic to a specific user.
必填参数:session_id、epic_id、user_id
unassign_epic_from_user 2 个参数 需填 2 项
Unassigns a specific epic (sets assigned user to null).
必填参数:session_id、epic_id
get_epic_statuses 2 个参数 需填 2 项
Lists the available statuses for epics within a specific project.
必填参数:session_id、project_id
list_milestones 2 个参数 需填 2 项
Lists milestones (sprints) within a specific project.
必填参数:session_id、project_id
create_milestone 5 个参数 需填 5 项
Creates a new milestone (sprint) within a project.
必填参数:session_id、project_id、name、estimated_start、estimated_finish
get_milestone 2 个参数 需填 2 项
Gets detailed information about a specific milestone by its ID.
必填参数:session_id、milestone_id
update_milestone 3 个参数 需填 3 项
Updates details of an existing milestone.
必填参数:session_id、milestone_id、kwargs
delete_milestone 2 个参数 需填 2 项
Deletes a milestone by its ID.
必填参数:session_id、milestone_id
get_milestone_stats 2 个参数 需填 2 项
Gets statistics (total points, completed points, etc.) for a specific milestone.
必填参数:session_id、milestone_id
get_project_members 2 个参数 需填 2 项
Lists members of a specific project.
必填参数:session_id、project_id
invite_project_user 4 个参数 需填 4 项
Invites a user to a project by email with a specific role.
必填参数:session_id、project_id、email、role_id
list_wiki_pages 2 个参数 需填 2 项
Lists wiki pages within a specific project.
必填参数:session_id、project_id
get_wiki_page 2 个参数 需填 2 项
Gets a specific wiki page by its ID.
必填参数:session_id、wiki_page_id
get_wiki_page_by_slug 3 个参数 需填 3 项
Gets a specific wiki page by its slug within a project.
必填参数:session_id、project_id、slug
logout 1 个参数 需填 1 项
Invalidates the current session_id.
必填参数:session_id
session_status 1 个参数 需填 1 项
Checks if the provided session_id is currently active and valid.
必填参数:session_id
服务介绍
Taiga MCP 桥接器
概述
Taiga MCP 桥接器是一个强大的集成层,它将 Taiga 项目管理平台与模型上下文协议(MCP)连接起来,使 AI 工具和工作流能够无缝地与 Taiga 的资源进行交互。
此桥接器为 AI 代理提供了全面的工具和资源,以实现以下功能:
- 在 Taiga 中创建和管理项目、史诗、用户故事、任务和问题
- 跟踪冲刺和里程碑
- 分配和更新工作项
- 查询关于项目工件的详细信息
- 管理项目成员和权限
通过使用 MCP 标准,此桥接器允许 AI 系统保持对项目状态的上下文感知,并以编程方式执行复杂的项目管理任务。
功能
全面的资源支持
该桥接器支持以下 Taiga 资源,并提供完整的 CRUD 操作:
- 项目:创建、更新和管理项目设置和元数据
- 史诗:管理跨越多个冲刺的大特性
- 用户故事:处理详细的需求和验收标准
- 任务:跟踪用户故事中的较小工作单元
- 问题:管理错误、问题和增强请求
- 冲刺(里程碑):在固定时间间隔内规划和跟踪工作
安装
该项目使用 uv 进行快速可靠的 Python 包管理。
前提条件
- Python 3.10 或更高版本
- uv 包管理器
基本安装
# Clone the repository
git clone https://github.com/your-org/pyTaigaMCP.git
cd pyTaigaMCP
# Install dependencies
./install.sh
开发安装
对于开发(包括测试和代码质量工具):
./install.sh --dev
手动安装
如果您更喜欢手动安装:
# Production dependencies only
uv pip install -e .
# With development dependencies
uv pip install -e ".[dev]"
配置
可以通过环境变量或 .env 文件配置桥接器:
| 环境变量 | 描述 | 默认值 |
|---|---|---|
TAIGA_API_URL |
Taiga API 的基础 URL | http://localhost:9000 |
SESSION_EXPIRY |
会话过期时间(秒) | 28800 (8 小时) |
TAIGA_TRANSPORT |
传输模式 (stdio 或 sse) | stdio |
REQUEST_TIMEOUT |
API 请求超时时间(秒) | 30 |
MAX_CONNECTIONS |
最大 HTTP 连接数 | 10 |
MAX_KEEPALIVE_CONNECTIONS |
最大保持活动连接数 | 5 |
RATE_LIMIT_REQUESTS |
每分钟最大请求数 | 100 |
LOG_LEVEL |
日志级别 | INFO |
LOG_FILE |
日志文件路径 | taiga_mcp.log |
在项目根目录中创建一个 .env 文件来设置这些值:
TAIGA_API_URL=https://api.taiga.io/api/v1/
TAIGA_TRANSPORT=sse
LOG_LEVEL=DEBUG
使用
使用 stdio 模式
将以下 JSON 粘贴到您的 Claude 应用程序或 Cursor 的 MCP 设置部分:
{
"mcpServers": {
"taigaApi": {
"command": "uv",
"args": [
"--directory",
"<path to local pyTaigaMCP folder>",
"run",
"src/server.py"
],
"env": {
"TAIGA_TRANSPORT": "<stdio|sse>",
"TAIGA_API_URL": "<Taiga API Url (ex: http://localhost:9000)",
"TAIGA_USERNAME": "<taiga username>",
"TAIGA_PASSWORD": "<taiga password>"
}
}
}
运行桥接器
启动 MCP 服务器:
# Default stdio transport
./run.sh
# For SSE transport
./run.sh --sse
或者手动运行:
# For stdio transport (default)
uv run python src/server.py
# For SSE transport
uv run python src/server.py --sse
传输模式
服务器支持两种传输模式:
- stdio (标准输入/输出) - 终端客户端的默认模式
- SSE (服务器发送事件) - 基于Web的传输,具有服务器推送功能
您可以使用以下几种方式设置传输模式:
- 使用
--sse标志与 run.sh 或 server.py(默认为 stdio) - 设置
TAIGA_TRANSPORT环境变量 - 将
TAIGA_TRANSPORT=sse添加到您的.env文件中
认证流程
此MCP桥使用基于会话的认证模型:
-
登录:客户端必须首先使用
login工具进行认证:session = client.call_tool("login", { "username": "your_taiga_username", "password": "your_taiga_password", "host": "https://api.taiga.io" # 可选 }) # 从响应中保存 session_id session_id = session["session_id"] -
使用工具和资源:在每个API调用中包含
session_id:# 对于资源,在URI中包含 session_id projects = client.get_resource(f"taiga://projects?session_id={session_id}") # 对于特定项目的资源 epics = client.get_resource(f"taiga://projects/123/epics?session_id={session_id}") # 对于工具,将 session_id 作为参数包含 new_project = client.call_tool("create_project", { "session_id": session_id, "name": "New Project", "description": "Description" }) -
检查会话状态:您可以检查会话是否仍然有效:
status = client.call_tool("session_status", {"session_id": session_id}) # 返回关于会话有效性和剩余时间的信息 -
注销:完成操作后,您可以注销以终止会话:
client.call_tool("logout", {"session_id": session_id})
示例:完整的项目创建工作流
这是一个包含史诗和用户故事的完整项目创建示例:
from mcp.client import Client
# Initialize MCP client
client = Client()
# Authenticate and get session ID
auth_result = client.call_tool("login", {
"username": "admin",
"password": "password123",
"host": "https://taiga.mycompany.com"
})
session_id = auth_result["session_id"]
# Create a new project
project = client.call_tool("create_project", {
"session_id": session_id,
"name": "My New Project",
"description": "A test project created via MCP"
})
project_id = project["id"]
# Create an epic
epic = client.call_tool("create_epic", {
"session_id": session_id,
"project_id": project_id,
"subject": "User Authentication",
"description": "Implement user authentication features"
})
epic_id = epic["id"]
# Create a user story in the epic
story = client.call_tool("create_user_story", {
"session_id": session_id,
"project_id": project_id,
"subject": "User Login",
"description": "As a user, I want to log in with my credentials",
"epic_id": epic_id
})
# Logout when done
client.call_tool("logout", {"session_id": session_id})
开发
项目结构
pyTaigaMCP/
├── src/
│ ├── server.py # MCP server implementation with tools
│ ├── taiga_client.py # Taiga API client with all CRUD operations
│ ├── tools.py # MCP tools definitions
│ └── config.py # Configuration settings with Pydantic
├── tests/
│ ├── conftest.py # Shared pytest fixtures
│ ├── unit/ # Unit tests
│ └── integration/ # Integration tests
├── pyproject.toml # Project configuration and dependencies
├── install.sh # Installation script
├── run.sh # Server execution script
└── README.md # Project documentation
测试
使用pytest运行测试:
# Run all tests
pytest
# Run only unit tests
pytest tests/unit/
# Run only integration tests
pytest tests/integration/
# Run tests with specific markers
pytest -m "auth" # Authentication tests
pytest -m "core" # Core functionality tests
# Run tests with coverage reporting
pytest --cov=src
调试和检查
使用附带的检查器工具进行调试:
# Default stdio transport
./inspect.sh
# For SSE transport
./inspect.sh --sse
# For development mode
./inspect.sh --dev
错误处理
所有API操作返回标准化的错误响应,格式如下:
{
"status": "error",
"error_type": "ExceptionClassName",
"message": "Detailed error message"
}
性能考虑
该桥实现了几种性能优化:
- 连接池:重用HTTP连接以提高性能
- 限速:防止Taiga API过载
- 重试机制:自动以指数退避方式重试失败的请求
- 会话清理:定期清理过期会话以释放资源
贡献
欢迎贡献!请随时提交Pull Request。
- Fork 仓库
- 创建你的功能分支 (
git checkout -b feature/amazing-feature) - 安装开发依赖 (
./install.sh --dev) - 进行你的修改
- 运行测试 (
pytest) - 提交你的更改 (
git commit -m 'Add some amazing feature') - 推送到分支 (
git push origin feature/amazing-feature) - 打开一个 Pull Request
许可证
此项目根据 MIT 许可证发布 - 详情请参阅 LICENSE 文件。
致谢
- Taiga 提供了出色的项目管理平台
- Model Context Protocol (MCP) 提供了标准化的AI通信框架
- 所有帮助塑造此项目的贡献者们