auth-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@auth-mcpsign me in with email user@example.com and password 123456"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Auth MCP Server
Fast, low-latency MCP server for authentication services
Optimized for real-time AI agent integration with LM Studio, Claude Desktop, and more.
🚀 Quick Start
# 1. Clone the repository
git clone https://github.com/wattlesol/auth-mcp.git
cd auth-mcp
# 2. Install dependencies
npm install
# 3. Configure environment
cp .env.example .env
# Edit .env with your API URLs
# 4. Test the server
./test-mcp-stdio.sh
# 5. Configure your AI agent (see Configuration section below)Related MCP server: rest_api_mcp
✨ Features
⚡ Low Latency - Direct stdio communication (< 10ms)
🔧 18 Dynamic Tools - Auto-loaded from Swagger/OpenAPI spec
🤖 AI Agent Ready - Works with LM Studio, Claude Desktop, etc.
🐳 Docker Support - Optional containerized deployment
📚 Complete Docs - Comprehensive guides and examples
📋 Configuration
For LM Studio
{
"mcpServers": {
"auth-mcp": {
"command": "node",
"args": ["/absolute/path/to/auth-mcp/auth-mcp"],
"env": {
"AUTH_API_BASE_URL": "https://your-auth-api.example.com",
"SWAGGER_URL": "https://your-auth-api.example.com/api-json"
}
}
}
}For Claude Desktop
Same configuration as above. Add to:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
For Qwen Coding Agent
Configuration is in .qwen/settings.json (see QWEN-SETUP.md for details)
🎯 Available Tools (18 Total)
The server dynamically loads tools from your Swagger/OpenAPI specification. Example tools:
Authentication & Sign In:
post_api_auth_signin- Sign in with email/passwordpost_api_auth_staff_signin- Staff sign in (branch-aware)post_api_auth_signup- Create new user accountpost_api_auth_signout- Sign out current user
User Info & Profile:
get_api_auth_me- Get current user informationput_api_auth_profile- Update user profile
OTP & Verification:
post_api_auth_otp_send- Send OTP to emailpost_api_auth_otp_verify- Verify OTP codepost_api_auth_verify_email- Verify email with OTPpost_api_auth_verify_phone- Verify phone with OTP
Password Management:
post_api_auth_forgot_request- Request password resetpost_api_auth_change_password- Change password
Token & Health:
post_api_auth_refresh_token- Refresh JWT tokenget_api_health- Health check endpoint
📚 Documentation
Document | Description |
📋 Ready-to-use configurations | |
🚀 Get started in 3 steps | |
🔧 Detailed setup guide | |
📖 Complete project overview | |
📘 MCP protocol details |
🧪 Testing
# Run automated tests
./test-mcp-stdio.sh
# Manual test
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}' | node auth-mcp🏗️ Architecture
AI Agent (LM Studio/Claude)
↓ stdio (JSON-RPC)
Auth MCP Server (Node.js)
↓ HTTPS
Backend Auth API (Swagger)📊 Performance
Latency: < 10ms (stdio communication)
Startup: ~2 seconds (loads Swagger spec)
Memory: ~50MB (Node.js + dependencies)
Protocol: MCP 2024-11-05
🐳 Docker Deployment
# Build
docker build -f Dockerfile.mcp -t auth-mcp-stdio .
# Run
docker run --rm -i --env-file .env auth-mcp-stdio🔧 Environment Variables
Copy .env.example to .env and configure:
AUTH_API_BASE_URL=https://your-auth-api.example.com
SWAGGER_URL=https://your-auth-api.example.com/api-json
AUTH_API_TIMEOUT=5000🛠️ Development
# Install dependencies
npm install
# Run HTTP server (legacy)
npm start
# Run MCP server (stdio)
npm run mcp
# Run tests
npm test📦 Project Structure
├── auth-mcp # Main launcher script
├── src/
│ ├── mcp-stdio-server.js # MCP server (stdio)
│ ├── api-client.js # Auth API client
│ ├── swagger-client.js # Swagger API client
│ └── swagger-tools-analyzer.js # Tool generator
├── config/
│ ├── lm-studio-config.json # LM Studio config
│ ├── claude-desktop-config.json # Claude Desktop config
│ └── mcp-config-docker.json # Docker config
├── docs/ # Documentation
├── test/ # Test files
├── .env.example # Example environment variables
└── package.json # Dependencies🤝 Contributing
This is a production-ready MCP server. Feel free to:
Add more tools
Improve error handling
Add monitoring/metrics
Extend documentation
📄 License
ISC
🆘 Support & Troubleshooting
Issues? Check these guides:
QWEN-SETUP.md - Qwen Coding Agent setup & troubleshooting
QWEN-TOOLS-FIX.md - Tools not showing? Read this
docs/QUICK-SETUP.md - Quick troubleshooting
docs/CONFIGURATION-GUIDE.md - Detailed help
Enable Debug Mode:
MCP_DEBUG=true node auth-mcp🎉 Success!
You now have a production-ready MCP server for AI agents!
Next Steps:
Configure your AI agent with the settings above
Test with: "Can you list the available authentication tools?"
Start using the tools in your AI conversations!
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityFmaintenanceA lightweight, fast MCP server that provides onchain capabilities for the LLMs and Agents.Last updated60250MIT
- AlicenseAqualityFmaintenanceA Model Context Protocol (MCP) server for authenticated REST APIs. Drop it into any project, point it at your API, and let AI agents call endpoints — with auto-login, 2FA support, Swagger spec fetch, and fuzzy endpoint search — all without writing a single line of auth code.Last updated3156MIT
- Alicense-qualityDmaintenanceMCP Server for AI agent identity and authorization. Create, verify, and manage agent identities with trust scores and scoped authorization tokens.Last updatedMIT
- AlicenseAqualityDmaintenanceMCP server for enterprise authentication and authorization — JWT validation, OIDC token inspection, OAuth 2.0 introspection, and role-based access control for AI agents.Last updated8MIT
Related MCP Connectors
MCP (Model Context Protocol) server for Appwrite
MCP Server for agents to onboard, pay, and provision services autonomously with InFlow
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Wattlesol/auth-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server