Bridges AWS API operations to AI agents for EC2 instance management, S3 bucket operations, Lambda function inspection, IAM policy analysis, and CloudWatch log retrieval. Uses your existing AWS credentials configured on the machine. Supports multi-account setups via role assumption.
Use cases
- DevOps inspects EC2 instances and security groups during incident response
- SRE retrieves CloudWatch logs to correlate errors with deployment timestamps
- Developer invokes Lambda functions with test payloads for debugging
- Security team reviews IAM policies to audit access patterns
- Platform engineer checks S3 bucket lifecycle policies for cost optimization
Key features
- Claude Desktop
- Claude Code
- Cursor
- VS Code
Frequently Asked Questions
- How does the agent authenticate to AWS?
- Uses AWS credentials from the environment (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY) or from ~/.aws/credentials. Supports IAM roles and STS temporary credentials.
- What AWS services are supported?
- Common services include EC2, S3, Lambda, IAM, CloudWatch, ECS, EKS, and RDS. Coverage varies. Check the GitHub repo for current service list.
- Can agents modify AWS resources?
- Yes, if the credentials have write permissions. Follow least-privilege principles and use read-only credentials for agents used primarily for querying.
Related
Related
3 Indexed items
Cloudflare MCP
Bridges AI agents to Cloudflare Workers, KV storage, R2 object storage, and D1 databases for edge deployment inspection and management. Agents can check Workers status, inspect KV namespaces, query D1 databases, and monitor R2 buckets directly from the coding environment.
Azure MCP
Connects AI agents to Azure resources including App Service, Cosmos DB, Key Vault, and Logic Apps for configuration inspection and diagnostic retrieval. Developers can query Azure settings and logs without Azure Portal. Uses Azure CLI credentials for authentication.
Kubernetes MCP
Go-native MCP server that interfaces directly with Kubernetes API for workload inspection, event monitoring, Helm release management, and log retrieval. Agents can debug cluster issues with RBAC-aware toolsets instead of copy-pasting kubectl output. Supports multiple cluster contexts.