MCP SSE Server POC
Enables creating and managing MCP server configurations with SSE streaming endpoints via a UI, deployable on Render with zero infrastructure.
README
MCP SSE Server POC
A proof-of-concept server for STDIO transport of Model Context Protocol (MCP) into instant Server-Sent Events (SSE) streaming, deployable as a service. Instant remote hosted MCP servers with zero infrastructure work.
Features
- Create and manage MCP server configurations via a simple UI
- Generate stable SSE endpoints for each configuration
- Stream real-time model responses via SSE
- Built with Express, Drizzle ORM, and PostgreSQL
- One-click deployment on Render
Local Development
Prerequisites
- Node.js (v18 or later)
- PostgreSQL database
Setup
- Clone this repository:
git clone https://github.com/yourusername/mcp-sse-poc.git
cd mcp-sse-poc
- Install dependencies:
npm install
- Set up your local PostgreSQL database and create a
.envfile with your database connection string:
DATABASE_URL=postgresql://username:password@localhost:5432/mcp_sse_db
- Generate and run migrations:
npm run generate
npm run migrate
- Start the development server:
npm run dev
- Open your browser and navigate to
http://localhost:3000
Deployment on Render
1. Push Your Code to GitHub/GitLab
Make sure your repository includes all the files in this project.
2. Create a Web Service on Render
- Log in to your Render Dashboard
- Click New → Web Service
- Connect your GitHub/GitLab repository
- Configure the service:
- Name: Choose a name (e.g.,
mcp-sse-poc) - Environment: Node
- Build Command:
npm install(this will trigger the postinstall script that builds and migrates) - Start Command:
npm start
- Name: Choose a name (e.g.,
- Click Create Web Service
3. Add a PostgreSQL Database
- In Render, click New → PostgreSQL Database
- Name it (e.g.,
mcp-sse-db) - Select the free plan
- Click Create Database
- Copy the provided
DATABASE_URLconnection string
4. Configure Environment Variables
- Go back to your Web Service
- Navigate to the Environment tab
- Add the following environment variable:
- Key:
DATABASE_URL - Value: Paste the connection string you copied
- Key:
5. Deploy
Render will automatically deploy your application. Once deployed, you can access it at the URL provided by Render.
Usage
- Open your deployed application in a browser
- Create a new MCP server configuration by entering a name and JSON configuration
- Save the configuration to generate an SSE URL
- Use the SSE URL in your client application to stream model responses
Example Configuration
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["@playwright/mcp@latest"]
}
}
}
Model Context Protocol (MCP)
The Model Context Protocol is a lightweight, STDIO-based specification for interacting with language models over a standard input/output interface. It allows for real-time streaming of model responses and is designed to be simple and extensible.
Core Concepts
-
STDIO Transport
- Input: JSON blob describing context messages
- Output: Incremental response tokens streamed to stdout
- Errors & Events: Non-blocking notifications on stderr
-
JSON Message Format
{ "context": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Translate to French: Hello, world!" } ], "stream": true } -
Server-Sent Events (SSE)
- Each JSON chunk becomes an SSE event
- Perfect mapping to MCP's unidirectional streaming model
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.