MCP Server Playground

A playground for Model Context Protocol (MCP) server built with TypeScript and Streamable HTTP transport with an OAuth Proxy for 3rd party authorization servers like Auth0.

Features

• MCP 2025-06-18 Compliant: Full compliance with the latest MCP specification including SSE resumability, tool annotations, and structured content.
• MCP Server implementation: HTTP-Based Streamable transport using @modelcontextprotocol/sdk with HTTP transport, session management, and tool execution.
• SSE Resumability: Clients can reconnect with Last-Event-ID header to resume receiving events after connection breaks, powered by EventStore.
• OAuth authentication/3rd party authorization: Implements an OAuth server for MCP clients with RFC 8707 Resource Indicators and RFC 9728 authorization discovery, delegating to Auth0.
• Storage: Pluggable storage abstraction (Memory/Valkey) with EventStore for SSE event persistence and replay.
• Session Management: Support stateful sessions by using replay of initial request for distributed deployments.
• Security: Strict Origin validation to prevent DNS rebinding attacks, WWW-Authenticate headers for authorization discovery.
• Tools:
  • aws-ecs: Investigate the ECS service, task and cloudwatch logs using AWS ECS, Cloudwatch Logs and Bedrock
  • aws-s3: Get the list of S3 buckets and objects
  • system-time: Get the current system time in various formats with timezone support
  • echo: Echo a message back with transformations, repetition
  • streaming: Simulate real-time streaming data with live updates
  • project: Find keywords in the current project directory
• Resources:
  • echo://documentation: Documentation for the echo tool (static resource)
  • echo://result/{resultId}: Access echo operation results (resource template)
• Prompts: echo

Documentation

• Architecture Overview - System design, data flows, and diagrams
• Environment Variables - Configuration options
• Tool Documentation (in each tool directory):
  • echo - Message echo with transformations
  • system-time - Current time with timezone support
  • streaming - Real-time data streaming simulation
  • project - Keyword search in project files
  • aws-ecs - ECS investigation with AI analysis
  • aws-s3 - S3 bucket and object listing
• Resource Documentation: src/resources/README.md - MCP resources overview

Why this project exists?

• The Model Context Protocol spec requires Dynamic Application Registration because it provides a standardized way for MCP clients to automatically register with new servers and obtain OAuth client IDs without user interaction. The main reason for this mechanism is because MCP clients can't know all possible services in advance and manual registration would create significant effort for users and it is not scalable. If do not support Dynamic Application Registration, then MCP clients need to provide OAuth client ID and secret to the server, which is not secure and not scalable.
• However, enabling Dynamic Application Registration (if supported) becomes a security risk because the endpoint is a public endpoint that anyone can create OAuth clients. It can easily be abused, such as by flooding with unwanted client registrations. Hence, Auth0 has disabled Dynamic Application Registration
• As a result, this project provides a way to enable Dynamic Application Registration for MCP server by using OAuth Proxy, but delegating authorization to 3rd party authorization server like Auth0, Github, Google, etc.

Endpoints

Endpoint	Description
GET /ping	Ping the server
POST /mcp	MCP protocol request with authentication
DELETE /mcp	Session termination
GET /.well-known/oauth-authorization-server	OAuth authorization server metadata
GET /.well-known/oauth-protected-resource	OAuth protected resources metadata
POST /oauth/register	Register a new MCP client
GET /oauth/authorize	Handle authorization request
POST /oauth/token	Handle token request
POST /oauth/revoke	Handle token revocation
GET /oauth/stats	Get OAuth service statistics
GET /oauth/auth0-callback	Handle Auth0 callback

Getting Started

Installation

1. Clone the repository:

   git clone <your-repo>
   cd mcp-server-playground
   

2. Install Bun (if not already installed):

   curl -fsSL https://bun.sh/install | bash
   

3. Install dependencies:

   bun install
   

4. Set up environment variables:

   cp .env.example .env
   

5. Set up the MCP server for local development

   bun run dev:setup
   

Helm Chart

helm repo add chrisleekr https://chrisleekr.github.io/helm-charts/
helm repo update
helm install mcp-server-playground chrisleekr/mcp-server-playground

Set up the MCP server for Cursor

1. Create MCP configuration file for local build

   Create a .cursor/mcp.json file in your project directory (for project-specific setup) or ~/.cursor/mcp.json in your home directory (for global setup):

   {
     "mcpServers": {
       "mcp-server-playground-cursor": {
         "type": "http",
         "url": "http://localhost:3000/mcp"
       }
     }
   }
   

Use MCP Inspector to test the server

1. Copy mcp-config.example.json to mcp-config.json

2. Edit mcp-config.json to point to the correct MCP server

3. Run the inspector

   docker compose up -d
   
   # Then run the inspector
   bunx @modelcontextprotocol/inspector -y --config ./mcp-config.json --server mcp-server-playground-inspector
   

   or

   docker compose up -d
   
   bun run test:inspector
   

Setup Auth0 for authorization

1. Create a new application in Auth0

   • Go to Auth0 Dashboard
   • Click on "Applications"
   • Click on "Create Application"
     • Name: MCP Server Playground
     • Application Type: Regular Web Application
   • Click on "Create"

2. Set up the application

   • Click on "Settings"
   • Set the following settings:
     • Allowed Callback URLs: http://localhost:3000/oauth/auth0-callback
     • Allowed Web Origins: http://localhost:3000

3. Create a new API

   • Click on "APIs"
   • Click on "Create API"
     • Name: MCP Server Playground
     • Identifier: urn:mcp-server-playground
     • JSON Web Token (JWT) Profile: Auth0
     • JSON Web Token (JWT) Signature Algorithm: RS256
   • Click on "Create"

How to make stateful session with multiple MCP Server instances?

When the MCP server is deployed as a cluster, it is not possible to make it stateful with multiple MCP Server instances because the transport is not shared between instances by design.

To make it truly stateful, I used Valkey to store the session id with the initial request.

When the request comes in to alternative MCP server instance, it will check if the session id is in the Valkey. If it is, it will replay the initial request and connect the transport to the server.

Inspired from https://github.com/modelcontextprotocol/modelcontextprotocol/discussions/102

See Architecture - Stateful Session Management for the detailed sequence diagram.

TODO

• Streaming is not working as expected. It returns the final result instead of streaming the data.

Screenshots

Metadata Discovery	Client Registration	Preparing Authorization

Authorization with 3rd party server	Request Authorization and acquire authorization code	Token Request and Authentication Complete

References

• Authorization
• Dynamic Application Registration
• Let's fix OAuth in MCP
• OAuth for MCP explained with a real-world example
• Treat the MCP server as an OAuth resource server rather than an authorization server
• HTTP + SSE MCP Server w/ OAuth by @NapthaAI