Skip to main content
Glama

Weather MCP Server

DEPLOYMENT.md3.07 kB
# AWS Lambda Deployment Guide This guide will help you deploy the Weather MCP server to AWS Lambda + API Gateway. ## Prerequisites 1. **AWS Account** - You need an AWS account 2. **AWS CLI** - Install from https://aws.amazon.com/cli/ 3. **AWS SAM CLI** - Install from https://docs.aws.amazon.com/serverless-application-model/latest/developerguide/install-sam-cli.html 4. **AWS Credentials** - Configure with `aws configure` ## Installation Steps ### 1. Install AWS CLI **Windows:** ```bash msiexec.exe /i https://awscli.amazonaws.com/AWSCLIV2.msi ``` **Mac:** ```bash brew install awscli ``` **Linux:** ```bash curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip" unzip awscliv2.zip sudo ./aws/install ``` ### 2. Install AWS SAM CLI **Windows:** ```bash msiexec.exe /i https://github.com/aws/aws-sam-cli/releases/latest/download/AWS_SAM_CLI_64_PY3.msi ``` **Mac:** ```bash brew install aws-sam-cli ``` **Linux:** ```bash wget https://github.com/aws/aws-sam-cli/releases/latest/download/aws-sam-cli-linux-x86_64.zip unzip aws-sam-cli-linux-x86_64.zip -d sam-installation sudo ./sam-installation/install ``` ### 3. Configure AWS Credentials Run: ```bash aws configure ``` Enter: - AWS Access Key ID - AWS Secret Access Key - Default region (e.g., `us-east-1`) - Default output format (use `json`) ## Deploy to AWS ### First Deployment (Guided) ```bash npm run deploy ``` This will: 1. Build your TypeScript code 2. Package the Lambda function 3. Ask you configuration questions 4. Deploy to AWS 5. Show you the API endpoint URL **Answer the prompts:** - Stack name: `weather-mcp` (or choose your own) - AWS Region: `us-east-1` (or your preferred region) - Confirm changes: `Y` - Allow SAM CLI IAM role creation: `Y` - Save arguments to config: `Y` ### Subsequent Deployments After the first deployment, use: ```bash npm run deploy:quick ``` This skips the guided questions and uses saved configuration. ## Testing Your Deployment After deployment, you'll see output like: ``` Outputs --------------------------------------------------------- WeatherMcpApi = https://xxxxxxxx.execute-api.us-east-1.amazonaws.com/mcp ``` Test with curl: ```bash curl -X POST https://YOUR-API-URL/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/list" }' ``` ## Monitoring and Logs View logs: ```bash sam logs -n WeatherMcpFunction --stack-name weather-mcp --tail ``` ## Cleanup (Delete Everything) When done testing: ```bash sam delete --stack-name weather-mcp ``` This removes all AWS resources and stops billing. ## Cost Estimate - **Free tier**: 1M requests/month FREE - **Beyond free tier**: ~$0.20 per 1M requests - **For testing**: Should be $0 ## Troubleshooting **Error: "AWS credentials not found"** - Run `aws configure` and enter your credentials **Error: "sam: command not found"** - Install AWS SAM CLI (see step 2) **Build errors:** - Run `npm run build` first to check for TypeScript errors - Ensure all dependencies are installed: `npm install`

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mkowalskizoovu/mcp-test'

If you have feedback or need assistance with the MCP directory API, please join our Discord server