- TypeScript 99.1%
- CSS 0.4%
- JavaScript 0.3%
- HTML 0.2%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
253db5ebc1## Problem The logout button only cleared inference provider authentication, leaving MCP OAuth tokens and server connections active. Users remained authenticated to MCP servers after logging out. ## Solution - **Clear MCP OAuth tokens**: Remove OAuth tokens and state for all MCP connections - **Disconnect all servers**: Remove all MCP server connections on logout - **Complete cleanup**: Comprehensive logout that clears all authentication state - **Enhanced confirmation**: Updated dialog to inform users about MCP disconnection ## Technical Implementation - Added MCP context integration to access connections and removal methods - Clear OAuth tokens from localStorage for each OAuth-enabled connection - Remove all MCP servers to properly disconnect and clean up connections - Maintained existing inference provider logout functionality ## User Experience - ✅ **Complete logout**: All authentication state cleared (inference + MCP) - ✅ **Clean slate**: No residual authentication data after logout - ✅ **Clear communication**: User informed about full scope of logout action - ✅ **Security**: No orphaned authentication tokens left behind ## Data Cleared on Logout - Inference provider API keys and OAuth tokens - MCP OAuth tokens and authentication state - Model selection preferences - All active MCP server connections Note: Conversation history remains intact as it's stored separately from auth data. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> |
||
| docs | ||
| src | ||
| .eslintrc.cjs | ||
| .gitignore | ||
| index.html | ||
| package-lock.json | ||
| package.json | ||
| postcss.config.js | ||
| README.md | ||
| tailwind.config.js | ||
| tsconfig.json | ||
| tsconfig.node.json | ||
| vite.config.ts | ||
Example Remote MCP Client
A React TypeScript application for connecting to multiple MCP (Model Context Protocol) servers and providing a conversational interface with tool calling capabilities.
Features
- 🔗 Multi-server MCP connections (HTTP/SSE transports)
- 🤖 Inference provider abstraction (starting with OpenRouter)
- 💬 Conversational interface with agent loops
- 🛠️ Real-time tool call visualization
- 🔍 MCP debugging and message tracing
- 📱 Responsive UI with left sidebar and chat interface
Development
Prerequisites
- Node.js (v18 or higher)
- npm, yarn, or pnpm
Getting Started
-
Install dependencies:
npm install -
Start the development server:
npm run dev -
Open http://localhost:3000 in your browser
Available Scripts
npm run dev- Start development servernpm run build- Build for productionnpm run preview- Preview production buildnpm run lint- Run ESLintnpm run test- Run testsnpm run test:ui- Run tests with UI
Architecture
The application is built with a modular architecture using React hooks and providers:
- InferenceProvider - Abstraction for LLM inference (OpenRouter, etc.)
- MCPProvider - Multi-server MCP connection management
- AgentLoop - Tool calling and conversation flow
- UI Components - Modular, reusable interface components
Technology Stack
- React 18 with TypeScript
- Vite for build tooling
- Tailwind CSS for styling
- MCP TypeScript SDK for protocol implementation
- Vitest for testing
Project Status
This is an active development project serving as both:
- A public example implementation of MCP client features
- A prototyping testbed for MCP protocol changes