secured-remote-mcp-server-on-aws
@komination
About secured-remote-mcp-server-on-aws
No overview available yet
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is secured-remote-mcp-server-on-aws?
secured-remote-mcp-server-on-aws is a solution that securely publishes an MCP Server using API Gateway (HTTP) with OAuth2 authentication as the entry point, routing through a private Lambda inside a VPC to access S3. It provides a simple example returning S3 file lists but can be extended by implementing different MCP Server logic in Lambda.
How to use secured-remote-mcp-server-on-aws?
Clone the repository, set up the devcontainer environment, configure .env and .auto.tfvars, bootstrap HCP Terraform with terraform init/plan/apply, then obtain an OAuth access token using the just get-token command. Finally, configure an MCP Client (e.g., VSCode's mcp.json) with the API Gateway endpoint URL and Bearer token.
Key features of secured-remote-mcp-server-on-aws
- OAuth2 authentication via API Gateway and Cognito
- Private Lambda execution inside a VPC
- S3 access through VPC endpoints
- Terraform-based infrastructure as code
- Devcontainer for reproducible development environment
- HCP Terraform for deployment management
- Supports both local and remote MCP clients
Use cases of secured-remote-mcp-server-on-aws
- Securely exposing an MCP Server to external clients with authentication
- Accessing private S3 buckets through a Lambda-based MCP endpoint
- Portfolio demonstration of production-grade AWS infrastructure deployment
- Extending the Lambda to access various other AWS resources via MCP
FAQ from secured-remote-mcp-server-on-aws
What authentication mechanism does it use?
OAuth2. The API Gateway entry point requires a Bearer token issued by AWS Cognito. Obtain the token via the provided just get-token command.
What are the prerequisites?
A devcontainer runtime environment, a GitHub-linked HCP Terraform account, and an AWS account with an IAM Identity Center user.
Where is the MCP Server code located?
In the /src directory, implemented with FastMCP in Python (main.py), with dependencies managed via uv and packaged as a Lambda Layer in /src/deps.
Does the server run inside a VPC?
Yes. The Lambda function is placed inside a VPC with private subnets. VPC endpoints for Lambda and S3 are used to avoid internet exposure.
What transport does the MCP server use?
HTTP. The server is exposed via API Gateway (HTTP type) and clients connect using the HTTP transport with a Bearer token in the Authorization header.
More Cloud & Infrastructure MCP servers
Supabase MCP Server
coleam00Supabase MCP server created in Python.
container-use
daggerDevelopment environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
MCP Server that interacts with Azure AI Foundry (experimental)
azure-ai-foundryA MCP Server for Azure AI Foundry: it's now moved to cloud, check the new Foundry MCP Server
Query | MCP server for Supabase
alexander-zuevQuery MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.
AWS Model Context Protocol (MCP) Server
alexei-ledA lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.
Comments