🧠 serverless-mcp-server

@eleva

About 🧠 serverless-mcp-server

A super simple Model Context Protocol (MCP) server deployed on AWS Lambda and exposed via Amazon API Gateway, deployed with Serverless Framework.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "serverless-mcp-server": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "node",
        "src/index.mjs"
      ]
    }
  }
}

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is serverless-mcp-server?

It is a minimal Model Context Protocol (MCP) server deployed on AWS Lambda and exposed via Amazon API Gateway using the Serverless Framework. Designed for developers who want to host MCP tools serverlessly on AWS.

How to use serverless-mcp-server?

Install dependencies with npm install, optionally install the open-source Serverless CLI globally (npm install -g osls), then run locally using serverless-offline (npm sls offline) or deploy to AWS with sls deploy. The endpoint is POST /mcp. Test with the MCP inspector or curl; an example add tool is included.

Key features of serverless-mcp-server

Minimal MCP server setup using @modelcontextprotocol/sdk
Deployed as a single AWS Lambda function
HTTP POST endpoint exposed via API Gateway at /mcp
Supports local development via serverless-offline
Includes a simple example tool (add) with JSON‑RPC interaction

Use cases of serverless-mcp-server

Hosting MCP tools on AWS without managing server infrastructure
Rapid prototyping and testing MCP servers locally before deploying
Integrating MCP capabilities into a serverless AWS stack
Building lightweight, scalable tool‑based AI agents

FAQ from serverless-mcp-server

What are the runtime requirements?

Node.js v22+ and the Serverless Framework v3+ (or the open‑source osls CLI) are required.

Can I use API Gateway V2 (HTTP API) instead of V1?

Yes. Change the events section in serverless.yml from http to httpApi and update local endpoint accordingly.

How do I test the server locally?

Run npm sls offline to start the server on http://localhost:3000/dev/mcp (V1) or http://localhost:3000/mcp (V2). Use the MCP inspector or curl to interact.

What tools are included by default?

Only a single example tool add that takes two numbers (a and b) and returns their sum. You can extend the server with your own tools.

Does deployment require an AWS account?

Yes. After running sls deploy, the server goes live on AWS. The URL is printed in the deployment output.

Frequently asked questions

What are the runtime requirements?

Node.js v22+ and the Serverless Framework v3+ (or the open‑source `osls` CLI) are required.

Can I use API Gateway V2 (HTTP API) instead of V1?

Yes. Change the `events` section in `serverless.yml` from `http` to `httpApi` and update local endpoint accordingly.

How do I test the server locally?

Run `npm sls offline` to start the server on `http://localhost:3000/dev/mcp` (V1) or `http://localhost:3000/mcp` (V2). Use the MCP inspector or curl to interact.

What tools are included by default?

Only a single example tool `add` that takes two numbers (`a` and `b`) and returns their sum. You can extend the server with your own tools.

Does deployment require an AWS account?

Yes. After running `sls deploy`, the server goes live on AWS. The URL is printed in the deployment output.

Comments

Basic information

More Cloud & Infrastructure MCP servers

Kilo IoT Platform

Kilo IoT

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a

Sample Serverless MCP Servers

aws-samples

Sample implementations of AI Agents and MCP Servers running on AWS Serverless compute

239

K8s MCP Server

alexei-led

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI syste

212

container-use

aluzzardi

Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

3.9K

Run Model Context Protocol (MCP) servers with AWS Lambda

awslabs

Run existing Model Context Protocol (MCP) stdio-based servers in AWS Lambda functions

373