mcpField
M
MCP HTTP Wrapper

MCP HTTP Wrapper

Local
github.com/manasniloroutDeveloper Tools0Updated 81w ago
Repository

About MCP HTTP Wrapper

MCP HTTP Wrapper runs MCP servers behind an AWS Lambda HTTP interface. It is for deploying configured MCP servers and exposing their tools through HTTP endpoints.

Key features

  1. 01AWS Lambda HTTP wrapper
  2. 02List tools by server name
  3. 03Call tools through POST endpoints
  4. 04Local development with Serverless Offline or Express
  5. 05Development and production deployment scripts

Use cases

  1. 01Expose MCP server tools through HTTP routes
  2. 02Run the service locally for development
  3. 03Deploy the wrapper to AWS

MCP support

It packages and runs MCP server implementations, handling communication with MCP clients. HTTP clients can list available tools and invoke them through server and tool routes.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP HTTP Wrapper

AWS Lambda HTTP wrapper for Model Context Protocol servers.

Prerequisites

  • Node.js (v18 or later)
  • AWS CLI configured with appropriate credentials
  • Serverless Framework

Installation

npm install
Setting up MCP Servers

Before testing or deployment, you need to install dependencies and build each MCP server:

# Navigate to each MCP server directory and install dependencies
cd mcp_servers/[server-name]
npm install
npm run build

# Repeat for each server directory under mcp_servers/

Local Development

To run the service locally with Serverless Offline:

npm run dev

To run the service with Express for easier debugging:

npm run dev:express

Deployment

Configure AWS Credentials

Before deploying, make sure you have AWS credentials configured:

aws configure
Prepare MCP Servers

Ensure you've built all MCP servers before deployment (see Setting up MCP Servers section).

Deploy to Development
npm run deploy

This will:

  1. Clean the dist directory
  2. Build the TypeScript code
  3. Package the necessary files including MCP servers
  4. Deploy to AWS using Serverless Framework
Deploy to Production
npm run deploy:prod

API Usage

List Available Tools
GET /{serverName}
Call a Tool
POST /{serverName}/{toolName}
{
  "param1": "value1",
  "param2": "value2"
}

Required headers must be included based on the specific MCP server configuration.

Project Structure

  • src/index.ts - Main Lambda handler function
  • src/mcp/mcp-server-config.ts - Configuration for available MCP servers
  • src/mcp/mcp-client-handler.ts - Handler for MCP client communications
  • mcp_servers/ - Directory containing MCP server implementations
  • serverless.yml - Serverless Framework configuration

Scripts

  • npm run build - Compiles TypeScript
  • npm run watch - Watches for TypeScript changes
  • npm run clean - Removes the dist directory
  • npm run dev - Runs the service locally
  • npm run deploy - Deploys to development
  • npm run deploy:prod - Deploys to production

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.