ProofHub MCP Server
Enables AI assistants to fetch ProofHub task details, comments, and bug tracker links from a URL, streamlining development workflows.
README
🔌 ProofHub MCP Server
A Model Context Protocol (MCP) server that bridges ProofHub's project management capabilities with AI assistants like Claude, GitHub Copilot, and Cursor. Paste a ProofHub task URL in your AI chat, and the agent automatically fetches task details, comments, and bug tracker links to help you complete development tasks faster.
🎯 What This Solves
As a developer working with ProofHub for task management, you normally have to:
- Open ProofHub in a browser
- Navigate to the task
- Read the description and all comments
- Copy relevant bug tracker links (Jira, Linear, GitHub Issues, etc.)
- Context-switch back to your code editor
With this MCP server, simply paste the ProofHub URL into your AI assistant, and it automatically:
- ✅ Fetches the complete task description
- ✅ Retrieves all comments and history
- ✅ Extracts bug tracker links from anywhere in the task
- ✅ Provides structured context for the AI to help you code
⚡ Features
- 🔒 Secure: API key stored in environment variables, never in code
- ⏱️ Rate Limit Handling: Automatically respects ProofHub's 25 req/10s limit with retry logic
- 🧹 HTML Cleanup: Strips HTML tags from descriptions/comments for clean AI consumption
- 🔗 Smart Link Extraction: Regex patterns detect bug tracker URLs across all text fields
- 🎯 One-Shot Tool:
get_task_with_bug_linksfetches everything in a single call - 🛡️ Error Handling: Graceful error messages with API status codes
🚀 Quick Start
1. Installation
npm install
2. Configuration
Create a .env file (use .env.example as template):
PROOFHUB_API_KEY=your_api_key_here
PROOFHUB_API_BASE=https://company.proofhub.com/api/v3
Getting your API key: Log in to ProofHub → Account Settings → Apps & Integrations → API → Generate new API key
3. Connect to Your AI Assistant
🤖 Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"proofhub": {
"command": "node",
"args": ["/absolute/path/to/proofhub-mcp/index.js"],
"env": {
"PROOFHUB_API_KEY": "your_key_here"
}
}
}
}
Config location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
💻 VS Code Copilot
Add to .vscode/mcp.json in your workspace or user settings:
{
"servers": {
"proofhub": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/proofhub-mcp/index.js"],
"env": {
"PROOFHUB_API_KEY": "your_key_here"
}
}
}
}
📋 Available Tools
| Tool | Description | Use Case |
|---|---|---|
proofhub_parse_url |
Extracts project/list/task IDs from a ProofHub URL | Parse URL before calling other tools |
proofhub_get_task |
Fetches complete task details (title, description, stage, custom fields, assignees) | Get full task context |
proofhub_get_comments |
Retrieves all task comments with timestamps | Review team discussions |
proofhub_get_task_with_bug_links |
⭐ One-shot: Fetches task + comments + auto-extracts bug tracker URLs | Most useful - get everything in one call |
proofhub_create_comment |
Posts a new comment on a task | Update task from your AI chat |
proofhub_get_task_history |
Fetches activity/stage change history | Track task evolution |
💡 Usage Examples
Example 1: Fetch Task Context
Simply paste a ProofHub URL in your AI chat:
Get context for this task:
https://kpi.proofhub.com/bappswift/#app/todos/project-7189443252/list-270280503800/task-514774338823
The AI will call proofhub_get_task_with_bug_links and return:
- Task title and description
- All comments (cleaned from HTML)
- List of bug tracker links found
- Stage, assignees, and custom fields
Example 2: Development Workflow
I need to work on this ProofHub task:
https://kpi.proofhub.com/.../task-514774338823
Fetch the task, find any Jira links, and help me understand what needs to be built.
The AI will:
- Fetch the complete task context
- Extract Jira/GitHub/Linear links
- Use your bug tracker MCP to fetch issue details
- Provide a comprehensive development plan
Example 3: Update Task
Add a comment to task 514774338823 in project 7189443252, list 270280503800:
"Completed the API endpoint implementation. Ready for review."
🤝 Contributing
Contributions welcome! Fork the repo, make your changes, and submit a pull request.
References
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。