A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
sample-serverless-mcp-server
A Github MCP Server implementation based on Amazon Lambda and Streamable HTTP protocol.
This project demonstrates how to transform the official TypeScript MCP Server to support Streamable HTTP protocol and deploy it via Amazon Lambda. The implementation leverages new features introduced in MCP v2025.03.26, including:
Stream transmission based on HTTP Chunked Transfer Encoding
Dynamic context priority control
Seamless integration with existing HTTP infrastructure
Streamable HTTP MCP protocol support
Elastic deployment based on Amazon Lambda
Optimized cost-performance balance

This project needs to set up a GITHUB_PERSONAL_ACCESS_TOKEN, which has been stored in Amazon Lambda environment variables.
Never submit your serverless.yml to a GitHub public repository.
# Clone repository
git clone https://gitlab.aws.dev/wsuam/sample-serverless-mcp-server.git
cd sample-serverless-mcp-server/src/github/
# Install dependencies
npm install
npm install -g osls
#Set your github personal access token in serverless.yml
cp serverless.example.yml serverless.yml
#edit serverless.yml , GITHUB_PERSONAL_ACCESS_TOKEN: <Your GitHub Personal Access Token>
# Test local
npm sls offline
# Deploy to AWS Lambda
npm sls deploy
The project utilizes the following architecture:
API Gateway: Handles HTTP requests
Lambda: Executes MCP Server logic
Streamable HTTP: Implements streaming responses
DynamoDB and S3 store request logs (this part is not ready yet).
npm sls offlinePull requests are welcome. Before submitting, please ensure:
This library is licensed under the MIT-0 License. See the LICENSE file.
Project is under active development. Issues and suggestions are welcome.
A Jetbrains IDE IntelliJ plugin aimed to provide coding agents the ability to leverage intelliJ's indexing of the codeba
Run Claude Code as an MCP server so any agent can delegate coding tasks to it
Browser automation using accessibility snapshots instead of screenshots