Taskboard MCP Server
Integrates GitHub Copilot Chat with your Taskboard instance to manage workspaces, boards, lists, and cards using natural language. It supports full task lifecycle operations, searching capabilities, and knowledge base queries via RAG.
README
Taskboard MCP Server Setup
Overview
This HTTP-based MCP (Model Context Protocol) server provides GitHub Copilot Chat with access to your Taskboard instance, allowing you to manage workspaces, boards, lists, and cards directly from Copilot.
Installation
- Install dependencies:
cd mcp-server
npm install
- Configure environment:
Create a
.envfile in themcp-serverdirectory:
# Taskboard API Configuration
TASKBOARD_API_URL=http://localhost:3000/api
TASKBOARD_AUTH_TOKEN=your_auth_token_here
MCP_SERVER_PORT=3001
Running the Server
Development
npm run dev
Production
npm start
The server will start on http://localhost:3001
GitHub Copilot Chat Integration
The .vscode/mcp.json file configures the MCP server for GitHub Copilot Chat:
{
"mcpServers": {
"taskboard": {
"url": "http://localhost:3001",
"env": {
"TASKBOARD_API_URL": "http://localhost:3000/api",
"TASKBOARD_AUTH_TOKEN": ""
}
}
}
}
Setting up Copilot Chat
- Open VS Code
- Go to Settings → Extensions → GitHub Copilot Chat
- Configure the MCP servers pointing to your local
.vscode/mcp.json - Ensure the MCP server is running (
npm start)
Available Tools
The MCP server exposes the following tools for Copilot Chat:
- list_workspaces - List all accessible workspaces
- list_boards - List boards in a workspace
- list_lists - List columns/lists in a board
- list_cards - List cards in a list
- search_cards - Search cards by title or description
- view_card - Get detailed card information
- update_card_description - Update a card's description
- update_card_status - Change a card's status
- create_card - Create a new card
- delete_card - Delete a card
- get_activity - Get user activity summary
- query_rag - Query the knowledge base using RAG
API Endpoints
Health Check
GET /health
MCP Endpoints
POST /mcp/v1/initialize - Initialize connection
POST /mcp/v1/tools/list - List available tools
POST /mcp/v1/tools/call - Call a specific tool
POST /mcp/v1/resources/list - List resources
POST /mcp/v1/prompts/list - List prompts
Example Copilot Chat Requests
- "List all my workspaces"
- "Show me boards in workspace 1"
- "Search for cards about authentication"
- "Update card 42 with description: 'In progress'"
- "Create a new card in list 3"
- "Query the knowledge base about setup process"
Troubleshooting
- Connection refused: Ensure the MCP server is running on port 3001
- Authentication error: Check that
TASKBOARD_AUTH_TOKENis valid - No tools available: Verify the server is properly initialized and responding to requests
- Port already in use: Change
MCP_SERVER_PORTin.envto use a different port
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。