@uniqueli/openwork 0.2.4 → 0.4.0

package/README.md

@@ -9,7 +9,7 @@
 
 A desktop interface for [deepagentsjs](https://github.com/langchain-ai/deepagentsjs) — an opinionated harness for building deep agents with filesystem capabilities, planning, and subagent delegation.
 
-**✨ Enhanced with Multiple Custom API Support** - Add unlimited OpenAI-compatible API providers with a single click!
+**✨ Enhanced with Multiple Custom API Support + MCP Integration** - Add unlimited OpenAI-compatible API providers and MCP servers with a single click!
 
 ![openwork screenshot](docs/screenshot.png)
 
@@ -42,12 +42,12 @@ Or configure them in-app via the settings panel.
 
 ## Supported Models
 
-| Provider  | Models                                                                                 |
-| --------- | -------------------------------------------------------------------------------------- |
-| Anthropic | Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Claude Opus 4.1, Claude Sonnet 4 |
-| OpenAI    | GPT-5.2, GPT-5.1, o3, o3 Mini, o4 Mini, o1, GPT-4.1, GPT-4o                            |
-| Google    | Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite |
-| **Custom**    | **Add unlimited custom providers!**                                |
+| Provider   | Models                                                                                                |
+| ---------- | ----------------------------------------------------------------------------------------------------- |
+| Anthropic  | Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Claude Opus 4.1, Claude Sonnet 4                |
+| OpenAI     | GPT-5.2, GPT-5.1, o3, o3 Mini, o4 Mini, o1, GPT-4.1, GPT-4o                                           |
+| Google     | Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite |
+| **Custom** | **Add unlimited custom providers!**                                                                   |
 
 ## ✨ Multiple Custom API Providers
 
@@ -68,6 +68,7 @@ Or configure them in-app via the settings panel.
 ### Supported Custom APIs
 
 Works with any OpenAI-compatible API:
+
 - **Chinese AI Providers**: Moonshot AI (Kimi), Zhipu AI (GLM), DeepSeek, Baichuan, etc.
 - **Self-hosted models**: vLLM, Text Generation WebUI, LocalAI, Ollama (with OpenAI compatibility)
 - **Cloud services**: Azure OpenAI, AWS Bedrock (with proxy), Cloudflare AI
@@ -76,6 +77,7 @@ Works with any OpenAI-compatible API:
 ### Example Configurations
 
 **Moonshot AI (Kimi)**
+
 ```
 ID: moonshot
 Display Name: Moonshot AI
@@ -84,6 +86,7 @@ Model Name: kimi-k2-turbo-preview
 ```
 
 **Zhipu AI (GLM)**
+
 ```
 ID: zhipu
 Display Name: Zhipu AI
@@ -92,40 +95,181 @@ Model Name: glm-4-plus
 ```
 
 **DeepSeek**
+
 ```
 ID: deepseek
 Display Name: DeepSeek
 Base URL: https://api.deepseek.com/v1
 Model Name: deepseek-chat
 ```
+
 Configure via Settings UI or by setting environment variables:
+
 ```bash
 CUSTOM_BASE_URL=https://api.example.com/v1
 CUSTOM_API_KEY=your-api-key
 CUSTOM_MODEL=your-model-name  # optional
 ```
 
+## 🔌 MCP Server Integration
+
+**New in v0.4.0**: Full support for Model Context Protocol (MCP) servers!
+
+### What is MCP?
+
+MCP (Model Context Protocol) is an open protocol that allows AI assistants to securely connect to external data sources and tools. With MCP, your agent can:
+
+- Access API documentation (YAPI, Swagger, etc.)
+- Query databases
+- Search the web
+- Interact with file systems
+- And much more!
+
+### How to Add MCP Servers
+
+1. Open the right panel in openwork
+2. Click the **"MCP"** section to expand it
+3. Click the **"+ 添加"** button
+4. Fill in the form:
+   - **传输类型**: STDIO (local process) or SSE (HTTP endpoint)
+   - **服务器ID**: Unique identifier (e.g., `yapi-devloper-mcp`)
+   - **显示名称**: Name shown in UI (e.g., `YAPI开发助手`)
+   - **命令** (STDIO only): Command to run (e.g., `npx`)
+   - **命令参数** (STDIO only): Arguments (e.g., `-y yapi-devloper-mcp@latest --stdio`)
+   - **环境变量**: Optional key-value pairs for sensitive data (API keys, etc.)
+   - **分类**: Choose a category for better organization
+5. Click **"测试连接"** to verify the configuration
+6. Click **"创建服务器"** to save
+
+### Example Configurations
+
+**YAPI Developer MCP**
+
+```
+ID: yapi-devloper-mcp
+Name: YAPI开发助手
+Type: STDIO
+Command: npx
+Args: -y yapi-devloper-mcp@latest --stdio
+Environment Variables:
+  YAPI_BASE_URL: https://yapi.jiaoyanyun.com
+  YAPI_USERNAME: your-username
+  YAPI_PASSWORD: your-password
+Category: API
+```
+
+**Context7 (Vector Context Service)**
+
+```
+ID: context7
+Name: Context7
+Type: STDIO
+Command: npx
+Args: -y @upstash/context7-mcp@latest
+Category: Custom
+```
+
+**Filesystem MCP**
+
+```
+ID: filesystem
+Name: 文件系统
+Type: STDIO
+Command: npx
+Args: -y @modelcontextprotocol/server-filesystem /path/to/allowed/directory
+Category: Filesystem
+```
+
+**GitHub MCP**
+
+```
+ID: github
+Name: GitHub
+Type: STDIO
+Command: npx
+Args: -y @modelcontextprotocol/server-github
+Environment Variables:
+  GITHUB_PERSONAL_ACCESS_TOKEN: ghp_xxxxxxxxxxxx
+Category: Development
+```
+
+**Brave Search MCP**
+
+```
+ID: brave-search
+Name: Brave搜索
+Type: SSE
+URL: https://sse.brave.search
+Environment Variables:
+  BRAVE_API_KEY: your-brave-api-key
+Category: Productivity
+```
+
+### Using MCP Tools
+
+Once connected, MCP tools are automatically available to your agent:
+
+- Tools are discovered and loaded automatically
+- Each server shows its connection status and tool count
+- Tools appear as regular LangChain tools in the agent's toolkit
+- Disconnect or disable servers to temporarily stop using their tools
+
+### Managing MCP Servers
+
+- **Connect/Disconnect**: Click the plug icon to connect/disconnect
+- **Enable/Disable**: Click the power icon to enable/disable a server
+- **Delete**: Click the trash icon to permanently remove a server
+- **View Status**: See real-time connection status (Connected/Connecting/Error/Disconnected)
+
 ## Changelog
 
+### v0.4.0 (2026-02-10)
+
+- 🔌 **MCP Integration**: 新增Model Context Protocol (MCP) 完整支持
+  - 支持STDIO和SSE两种传输方式
+  - 可视化MCP服务器管理界面（右侧面板新增MCP分区）
+  - 支持环境变量配置（用于API密钥等敏感信息）
+  - 自动将MCP工具转换为LangChain工具
+  - Agent运行时自动加载已连接的MCP工具
+  - 实时显示连接状态和工具数量
+  - 支持测试连接功能
+  - 已测试：YAPI Developer MCP、Context7等
+
+### v0.3.0 (2026-02-09)
+
+- 🚀 **Skills System Major Upgrade**: 技能系统重大升级
+  - ⚡ **Performance**: 将所有文件操作转换为异步I/O，解决UI阻塞问题
+  - 🔒 **Security**: 新增完整的输入验证系统，防止注入攻击和资源耗尽
+  - 💾 **Memory**: 实现LRU缓存机制（最大100个技能），防止内存泄漏
+  - 🎯 **Skill Combination**: 新增技能组合功能，支持跨学科专业知识整合
+  - 📝 **Version Management**: 为所有技能添加语义化版本控制
+  - 🛠️ **Error Handling**: 增强错误处理系统，提供中文错误消息和恢复建议
+- 🐛 **UI Fix**: 修复创建技能对话框在From Template模式下窗口过大、关闭按钮不可见的问题
+
 ### v0.2.4 (2026-02-06)
+
 - ✨ **聊天建议卡片**: 新对话空状态下显示可点击的建议卡片（文件整理、内容创作、文档处理），点击即可快速开始对话
 
 ### v0.2.3 (2026-02-04)
+
 - ✨ **Skills System**: 新增技能配置系统，支持 12 个内置技能和自定义技能创建
 - 🐛 修复 `deleteUserSkill` 误删所有技能记录的严重 Bug
 - 🐛 修复 Switch 组件、创建技能对话框、技能过滤等多个问题
 - ⚡ 技能初始化改为懒加载，提升启动性能
 
 ### v0.2.2 (2026-xx-xx)
+
 - ✨ 支持多个自定义 API 配置
 - 🔧 动态 Provider 系统
 
 ### v0.2.1 (2026-01-19)
+
 - 🐛 **Critical Fix**: Fixed "Missing credentials" error for users without OpenAI API key
 - 🔧 Custom API now works correctly even when OPENAI_API_KEY is not set in environment
 - 📝 Improved logging for debugging custom API configurations
 
 ### v0.2.0 (2026-01-18)
+
 - ✨ **Multiple Custom API Providers**: Add unlimited custom providers via UI
 - 🎨 **Improved UX**: One-click provider addition with "+ 添加Provider" button
 - 🔧 **Better Configuration**: Each provider has its own name, base URL, API key, and model
@@ -133,6 +277,7 @@ CUSTOM_MODEL=your-model-name  # optional
 - 📝 **Simplified Settings**: Cleaner settings dialog focused on standard providers
 
 ### v0.1.0 (2026-01-15)
+
 - 🎉 Initial release with basic custom API support
 - 🔑 Single custom API configuration via Settings