MCP Lambda Server
@markvp
About MCP Lambda Server
An AWS Serverless Application Model that operates as an MCP server via serverless AWS resources
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-lambda-layer": {
"command": "npx",
"args": [
"@markvp/mcp-lambda-sam",
"deploy"
]
}
}
}Tools
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 MCP Lambda Server?
MCP Lambda Server is a serverless implementation of the Model Context Protocol (MCP) built on AWS Lambda and SAM. It exposes two interfaces: a System Configuration API for administrators to register tools, resources, and prompts, and a System Usage interface for clients to establish SSE connections and send JSON-RPC commands. It is intended for developers and administrators deploying MCP servers on AWS.
How to use MCP Lambda Server?
Deploy using npx @markvp/mcp-lambda-sam deploy, the AWS SAM CLI, or via the AWS Serverless Application Repository (SAR). After deployment, administrators use the Registration API (endpoints under /register) to manage tools. Clients connect to the /sse endpoint, receive a session ID, then send JSON-RPC messages to /message?sessionId=.... All requests require AWS SigV4 signed IAM authentication.
Key features of MCP Lambda Server
- Serverless MCP implementation using AWS Lambda and DynamoDB
- Administrative registration of tools, resources, and prompts
- Client SSE streaming and JSON-RPC message handling
- IAM-based authentication for all endpoints
- Supports multiple deployment methods (SAR, npx, programmatic)
- Session persistence via DynamoDB Session Table
- Dynamic invocation of registered Lambda tools by ARN
Use cases of MCP Lambda Server
- Deploy a fully serverless MCP server for AI assistants or agents
- Register custom Lambda functions as MCP tools with defined schemas
- Provide an administrative interface for managing tool inventory and permissions
- Enable clients to stream MCP responses over SSE with session isolation
FAQ from MCP Lambda Server
How do I deploy MCP Lambda Server?
Use npx @markvp/mcp-lambda-sam deploy, the AWS SAM CLI (sam build && sam deploy --guided), or the AWS Serverless Application Repository (SAR). You need AWS CLI, SAM CLI, Node.js 20+, and an AWS account with permissions to create Lambda functions, DynamoDB tables, IAM roles, and SQS queues.
What authentication is required for endpoints?
All endpoints use IAM authentication via AWS SigV4. Administrators need lambda:InvokeFunctionUrl permission on the registration function; clients need the same permission on the MCP function.
How do I register a new tool?
Send a POST request to ${REGISTRATION_URL}/register with a JSON body containing type ("tool"), name, description, lambdaArn, and parameters. Use awscurl or any AWS SigV4 signed HTTP client.
Where is session state persisted?
Session state is stored in a DynamoDB Session Table. The table is created during deployment and used by the MCP Lambda function.
What are common client errors?
401 (invalid/missing credentials), 403 (insufficient permissions), 404 (invalid session ID), and 429 (rate limit exceeded). Troubleshoot by verifying AWS credentials, IAM permissions, session ID validity, and network connectivity.
More Cloud & Infrastructure MCP servers
Mcp K8s Go
strowkMCP server connecting to Kubernetes
🐋 Docker MCP server
ckreilingMCP server for Docker
GCP MCP
eniayomiA Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your Google Cloud Platform environment. This allows for natural language querying and management of your GCP resources during conversations.
container-use
aluzzardiDevelopment environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
tfmcp: Terraform Model Context Protocol Tool
nwiizo🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing plans, applying configurations, and managing state with Claude Desktop integrati
Comments