Connect Amazon Web Services to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.
What you can do with the Amazon Web Services MCP server
Ask your agent in plain language. Each of these maps to a real tool on the server.
Use the manage s3 tool in Amazon Web Services
Use the manage cloud watch tool in Amazon Web Services
Use the manage ec2 instances tool in Amazon Web Services
Use the manage lambda tool in Amazon Web Services
Use the manage iam tool in Amazon Web Services
Use the manage dynamo db tool in Amazon Web Services
Supported Tools
manage_s3
Manage S3
Manage Amazon S3 buckets and objects. Supports listing buckets, creating and deleting buckets, listing objects within a bucket, retrieving object metadata, deleting objects, and copying objects between locations. This tool covers S3 management operations — it does not handle binary upload or download.
manage_cloudwatch
Manage CloudWatch
Manage Amazon CloudWatch metrics and alarms. Supports listing and describing alarms, creating or updating metric alarms, deleting alarms, retrieving metric statistics, and listing available metrics. Use this to monitor AWS resources, configure alerting thresholds, and query time-series metric data.
manage_ec2_instances
Manage EC2 Instances
List, start, stop, terminate, or reboot Amazon EC2 instances. Use the list operation to discover instances with filtering by IDs, states, or tags. Use action operations to control instance lifecycle.
manage_lambda
Manage Lambda
Manage AWS Lambda functions: list functions, get details, invoke a function with a JSON payload, update configuration (memory, timeout, environment variables, layers, VPC, tracing), or delete a function. Set the **operation** field to choose the action.
manage_iam
Manage IAM
Manage AWS IAM users, roles, and policy attachments. Supports listing, creating, and deleting users; listing and inspecting roles; and attaching or detaching managed policies to users and roles.
manage_dynamodb
Manage DynamoDB
Manage AWS DynamoDB tables and items. Supports listing, describing, creating, and deleting tables, as well as putting, getting, querying, scanning, and deleting items.
Accepts plain JSON objects for items and keys -- automatic conversion to/from DynamoDB attribute format is handled internally.
manage_sqs
Manage SQS
Manage Amazon SQS (Simple Queue Service) queues and messages. Supports listing queues, creating and deleting queues, sending and receiving messages, deleting messages, retrieving queue attributes, and purging all messages from a queue.
manage_sns
Manage SNS
Manage AWS SNS (Simple Notification Service) topics and subscriptions. Supports listing topics, creating and deleting topics, publishing messages, listing subscriptions for a topic, subscribing endpoints (email, SQS, Lambda, HTTP/HTTPS), and unsubscribing. Set the **operation** field to choose the action.
Enable Amazon Web Services in Metorial. In your Metorial portal, enable the Amazon Web Services MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
Sign in. Select Add and sign in to load Amazon Web Services tools.
Enable Amazon Web Services in Metorial. In your Metorial portal, enable the Amazon Web Services MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add a custom MCP server. On ChatGPT web, open Plugins, select +, then Add custom MCP server.
Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>), choose OAuth and accept the risk notice.
Create and install the plugin. Select Create as a plugin, install it and sign in to load Amazon Web Services tools.
Enable Amazon Web Services in Metorial. In your Metorial portal, enable the Amazon Web Services MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add Metorial to your MCP config. Use ~/.cursor/mcp.json for every project, or .cursor/mcp.json for one.
Sign in. Open Customize in the sidebar, find Metorial and sign in to load Amazon Web Services tools.
{
"mcpServers":{
"metorial":{
"url":"<your-magic-mcp-url>"
}
}
}
Enable Amazon Web Services in Metorial. In your Metorial portal, enable the Amazon Web Services MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add the server over HTTP. Add --scope user to use it in every project.
Sign in. Run /mcp, select Metorial and sign in to load Amazon Web Services tools.
claude mcp add --transport http metorial <your-magic-mcp-url>
Enable Amazon Web Services in Metorial. In your Metorial portal, enable the Amazon Web Services MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add the server and sign in. The Codex CLI, IDE extension and ChatGPT desktop app share this config.
Check the connection. Type /mcp in Codex to see Metorial and its Amazon Web Services tools.
codex mcp add metorial --url <your-magic-mcp-url>
codex mcp login metorial
Run Amazon Web Services through the Metorial gateway
One governed layer for every app your agents reach, not a separate connector per tool.
Give Amazon Web Services and every other app to your whole team through one MCP gateway, behind your SSO.
Scope which teams and agents can use Amazon Web Services tools with role-based access control, and trace every call.
Prefer to run it yourself? Metorial is open source and self-hostable.
More integrations teams use with Amazon Web Services
Manage AWS cloud infrastructure and services. Launch, configure, and terminate EC2 instances. Deploy and invoke Lambda functions. Create and manage S3 buckets and objects with upload, download, versioning, and lifecycle policies. Provision and manage RDS relational databases and DynamoDB NoSQL tables. Configure VPCs, subnets, security groups, and load balancers. Manage IAM users, roles, and permission policies. Set up CloudWatch alarms, metrics, and dashboards for monitoring. Create SNS topics and SQS queues for messaging. Define CloudFormation stacks for infrastructure as code. Configure EventBridge rules to route events across services. Manage encryption keys with KMS and secrets with Secrets Manager. Access AI/ML services including Bedrock foundation models, SageMaker, Rekognition, Comprehend, Translate, Polly, and Transcribe. Set up CI/CD pipelines with CodePipeline, CodeBuild, and CodeDeploy. Manage container orchestration with ECS and EKS. Configure Route 53 DNS, CloudFront CDN, and API Gateway endpoints.
Frequently asked questions
Common questions about connecting Amazon Web Services to AI agents with Metorial.
How many tools does the Amazon Web Services MCP server have?
The Amazon Web Services MCP server exposes 8 tools, including Manage S3, Manage CloudWatch, Manage EC2 Instances. Each one is governed and traced through Metorial.
Does the Amazon Web Services MCP server support triggers?
Amazon Web Services exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
Which AI clients can use the Amazon Web Services MCP server?
Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Amazon Web Services MCP server through the same Metorial URL.
How do I give only some teams access to Amazon Web Services?
Use role-based access control to decide which teams, users, and agents can use Amazon Web Services and which of its tools they can call.
Can I self-host the Amazon Web Services MCP server?
Yes. Metorial is open source, so you can run the Amazon Web Services MCP server yourself or use the hosted gateway.
Connect Amazon Web Services to production AI agents
See how Metorial gives your team governed access to Amazon Web Services, with tracing and security controls built in.