Chat ApplicationCAUTION
基于MCP(Model Context Protocol)的智能聊天应用,支持Web和桌面环境。集成OpenAI/Anthropic API,提供MCP服务器的所有工具能力。简洁现代的UI设计,支持跨平台部署。
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
基于 Model Context Protocol 的智能聊天应用,支持Web和桌面环境。
项目介绍
MCP聊天应用是一个基于Vue.js构建的现代化聊天界面,支持通过Model Context Protocol (MCP)与各种服务和工具进行交互。MCP是Anthropic推出的开放协议标准,允许AI模型直接调用诸如数据库、文件系统、浏览器自动化、第三方mcp服务等。
本应用同时支持Web端和桌面端(基于Electron),并且集成了OpenAI和Anthropic两种主流大模型服务。
应用界面展示
核心功能特点
- 简洁现代的聊天界面设计
- MCP协议支持:与外部工具和服务进行无缝交互
- 多模型支持:兼容OpenAI和Anthropic两种API格式
- 自定义配置:可配置API密钥、基础URL和模型选项
- 可扩展架构:支持添加自定义工具和服务
- 桌面应用:提供跨平台(Windows/Mac/Linux)桌面体验
- 浏览器自动化:支持AI控制浏览器执行任务
- 本地服务:集成MCP后端服务提供强大功能
系统要求
- Node.js: v16.0.0+
- npm: v8.0.0+
- 现代浏览器:Chrome, Firefox, Safari, Edge最新版本
- 操作系统:Windows 10+, macOS 10.15+, Ubuntu 20.04+(桌面版)
快速开始
安装依赖
npm install
配置环境变量(非必要)
复制.env.example文件到.env,并填入必要的API密钥和配置:
cp .env.example .env
编辑.env文件设置以下内容:
VITE_API_KEY=your_api_key_here VITE_MODEL_PROVIDER=openai # 或 anthropic MCP_SERVER_PORT=3001 # MCP服务器端口
启动应用
Web应用开发模式
# 启动前端开发服务器 npm run dev # 在另一个终端启动MCP后端服务 npm run mcp:server
桌面应用开发模式
# 启动Electron应用 npm run electron:dev # 在另一个终端启动MCP后端服务 npm run mcp:server
运行应用
Web应用
npm run dev # 在另一个终端启动MCP后端服务 npm run mcp:server
桌面应用
# 启动Electron应用 npm run electron:dev # 在另一个终端启动MCP后端服务 npm run mcp:server
构建应用
Web应用构建
npm run build
桌面应用构建
# 构建所有平台版本 npm run electron:build # 构建特定平台版本 npm run electron:buildwin # Windows npm run electron:buildmac # macOS npm run electron:buildlinux # Linux
详细使用说明
配置模型设置
- 打开应用后,点击右上角的⚙️设置图标
- 在设置面板中配置:
- 模型提供商:选择OpenAI或Anthropic
06e6cc01c3c2OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-chat -- npx -y [email protected]
{
"mcpServers": {
"mcp-chat": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
GPT-4o | read | OpenAI最新的多模态模型 |
自定义模型 | read | 手动添加的自定义模型 |
Trust audit
CAUTIONgrade B · trust 86/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (3)
.env
.env
@ant-design/icons, @anthropic-ai/sdk, @modelcontextprotocol/sdk, @types/katex, antd, axios, body-parser, cors
Gates applied: no_behavioural_pass.
06e6cc01c3c2full audit observations/trust-audit/mcp-server/machaojin1917939763__chat-application.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 06e6cc01c3c2 | CAUTION | B | 86 | first audit |
Questions
What is the Chat Application MCP server?
基于MCP(Model Context Protocol)的智能聊天应用,支持Web和桌面环境。集成OpenAI/Anthropic API,提供MCP服务器的所有工具能力。简洁现代的UI设计,支持跨平台部署。
What tools does Chat Application expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Chat Application safe to connect to an agent?
With care. The audit graded it B (86/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Chat Application need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (06e6cc01c3c2), read on 2026-10-07. The repository is watched and re-audited when it changes.