AWS MCP Servers

What is the Model Context Protocol (MCP) and how does it work with AWS MCP Servers?

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

An MCP Server is a lightweight program that exposes specific capabilities through the standardized Model Context Protocol. Host applications (such as chatbots, IDEs, and other AI tools) have MCP clients that maintain 1:1 connections with MCP servers. Common MCP clients include agentic AI coding assistants (like Q Developer, Cline, Cursor, Windsurf) as well as chatbot applications like Claude Desktop, with more clients coming soon. MCP servers can access local data sources and remote services to provide additional context that improves the generated outputs from the models.

AWS MCP Servers use this protocol to provide AI applications access to AWS documentation, contextual guidance, and best practices. Through the standardized MCP client-server architecture, AWS capabilities become an intelligent extension of your development environment or AI application.

AWS MCP servers enable enhanced cloud-native development, infrastructure management, and development workflows—making AI-assisted cloud computing more accessible and efficient.

The Model Context Protocol is an open source project run by Anthropic, PBC. and open to contributions from the entire community. For more information on MCP, you can find further documentation](#cline_mcp_settingsjson)here

Important Notice:On May 26th, 2025, Server Sent Events (SSE) support was removed from all MCP servers in their latest major versions. This change aligns with the Model Context Protocol specification'sbackwards compatibility guidelines.

We are actively working towards supportingStreamable HTTP, which will provide improved transport capabilities for future versions.

- AWS Documentation MCP Server- Get latest AWS docs and API references

- AWS CDK MCP Server- AWS CDK development with security compliance and best practices
- AWS Terraform MCP Server- Terraform workflows with integrated security scanning
- AWS CloudFormation MCP Server- Direct CloudFormation resource management via Cloud Control API

- Amazon EKS MCP Server- Kubernetes cluster management and application deployment
- Amazon ECS MCP Server- Container orchestration and ECS application deployment
- Finch MCP Server- Local container building with ECR integration

- AWS Serverless MCP Server- Complete serverless application lifecycle with SAM CLI
- AWS Lambda Tool MCP Server- Execute Lambda functions as AI tools for private resource access

- AWS Support MCP Server- Help users create and manage AWS Support cases

- Amazon Bedrock Knowledge Bases Retrieval MCP Server- Query enterprise knowledge bases with citation support
- Amazon Kendra Index MCP Server- Enterprise search and RAG enhancement
- Amazon Q index MCP Server- Data accessors to search through enterprise's Q index
- Amazon Nova Canvas MCP Server- AI image generation with text and color guidance
- Amazon Rekognition MCP Server- Analyze images using computer vision capabilities
- Amazon Bedrock Data Automation MCP Server- Analyze documents, images, videos, and audio files

- Amazon DynamoDB MCP Server- Complete DynamoDB operations and table management
- Amazon Aurora PostgreSQL MCP Server- PostgreSQL database operations via RDS Data API
- Amazon Aurora MySQL MCP Server- MySQL database operations via RDS Data API
- Amazon Aurora DSQL MCP Server- Distributed SQL with PostgreSQL compatibility
- Amazon DocumentDB MCP Server- MongoDB-compatible document database operations
- Amazon Neptune MCP Server- Graph database queries with openCypher and Gremlin
- Amazon Keyspaces MCP Server- Apache Cassandra-compatible operations
- Amazon Timestream for InfluxDB MCP Server- InfluxDB-compatible operations
- Amazon Redshift MCP Server- Provides tools to discover, explore, and query Amazon Redshift clusters and serverless workgroups

- Amazon OpenSearch MCP Server- OpenSearch powered search, Analytics, and Observability

- Amazon ElastiCache MCP Server- Complete ElastiCache operations
- Amazon ElastiCache / MemoryDB for Valkey MCP Server- Advanced data structures and caching with Valkey
- Amazon ElastiCache for Memcached MCP Server- High-speed caching operations

- AWS IAM MCP Server- Comprehensive IAM user, role, group, and policy management with security best practices
- Git Repo Research MCP Server- Semantic code search and repository analysis
- Code Documentation Generation MCP Server- Automated documentation from code analysis
- AWS Diagram MCP Server- Generate architecture diagrams and technical illustrations
- Frontend MCP Server- React and modern web development guidance
- Synthetic Data MCP Server- Generate realistic test data for development and ML
- OpenAPI MCP Server- Dynamic API integration through OpenAPI specifications

- Amazon SNS / SQS MCP Server- Event-driven messaging and queue management
- Amazon MQ MCP Server- Message broker management for RabbitMQ and ActiveMQ
- AWS Step Functions Tool MCP Server- Execute complex workflows and business processes
- Amazon Location Service MCP Server- Place search, geocoding, and route optimization
- OpenAPI MCP Server- Dynamic API integration through OpenAPI specifications

- Cost Analysis MCP Server- Pre-deployment cost estimation and optimization
- AWS Cost Explorer MCP Server- Detailed cost analysis and reporting
- Amazon CloudWatch Logs MCP Server- Log analysis and operational troubleshooting
- AWS Managed Prometheus MCP Server- Prometheus-compatible operations

- Core MCP Server- Start here: intelligent planning and MCP server orchestration
- AWS Documentation MCP Server- Get latest AWS docs and API references
- Git Repo Research MCP Server- Semantic search through codebases and repositories

- AWS CDK MCP Server- CDK development with security best practices and compliance
- AWS Terraform MCP Server- Terraform with integrated security scanning and best practices
- AWS CloudFormation MCP Server- Direct AWS resource management through Cloud Control API

- Frontend MCP Server- React and modern web development patterns with AWS integration
- AWS Diagram MCP Server- Generate architecture diagrams as you design
- Code Documentation Generation MCP Server- Auto-generate docs from your codebase
- OpenAPI MCP Server- Dynamic API integration through OpenAPI specifications

- Amazon EKS MCP Server- Kubernetes cluster management and app deployment
- Amazon ECS MCP Server- Containerize and deploy applications to ECS
- Finch MCP Server- Local container building with ECR push
- AWS Serverless MCP Server- Full serverless app lifecycle with SAM CLI

- Synthetic Data MCP Server- Generate realistic test data for your applications

- Amazon Bedrock Knowledge Bases Retrieval MCP Server- Query enterprise knowledge with citations
- Amazon Kendra Index MCP Server- Enterprise search and document retrieval
- Amazon Q index MCP Server- Data accessors to search through enterprise's Q index
- AWS Documentation MCP Server- Official AWS documentation for technical answers

- Amazon Nova Canvas MCP Server- Generate images from text descriptions and color palettes
- Amazon Rekognition MCP Server- Analyze images using computer vision capabilities
- Amazon Bedrock Data Automation MCP Server- Analyze uploaded documents, images, and media

- Amazon Location Service MCP Server- Location search, geocoding, and business hours
- Cost Analysis MCP Server- Answer cost questions and provide estimates
- AWS Cost Explorer MCP Server- Detailed cost analysis and spend reports

- Amazon DynamoDB MCP Server- NoSQL database operations and table management
- Amazon Aurora PostgreSQL MCP Server- PostgreSQL operations via RDS Data API
- Amazon Aurora MySQL MCP Server- MySQL operations via RDS Data API
- Amazon Aurora DSQL MCP Server- Distributed SQL database operations
- Amazon DocumentDB MCP Server- MongoDB-compatible document operations
- Amazon Neptune MCP Server- Graph database queries and analytics
- Amazon Keyspaces MCP Server- Cassandra-compatible operations
- Amazon Timestream for InfluxDB MCP Server- InfluxDB-compatible operations

- Amazon ElastiCache / MemoryDB for Valkey MCP Server- Advanced caching and data structures
- Amazon ElastiCache for Memcached MCP Server- High-speed caching layer

- AWS Lambda Tool MCP Server- Execute Lambda functions for private resource access
- AWS Step Functions Tool MCP Server- Complex multi-step workflow execution
- Amazon SNS / SQS MCP Server- Event-driven messaging and queue processing
- Amazon MQ MCP Server- Message broker operations

- Amazon CloudWatch Logs MCP Server- Log analysis and operational troubleshooting
- AWS Cost Explorer MCP Server- Cost monitoring and spend analysis
- AWS Managed Prometheus MCP Server- Prometheus-compatible operations

Seesrc/mcp-lambda-handler/README.mdfor full usage, installation, and development instructions.

Each server has specific installation instructions. Generally, you can:
- InstalluvfromAstral
- Install Python usinguv python install 3.10
- Configure AWS credentials with access to required services
- Add the server to your MCP client configuration

{ "mcpServers": { "awslabs.core-mcp-server": { "command": "uvx", "args": [ "awslabs.core-mcp-server@latest" ], "env": { "FASTMCP_LOG_LEVEL": "ERROR" } }, "awslabs.nova-canvas-mcp-server": { "command": "uvx", "args": [ "awslabs.nova-canvas-mcp-server@latest" ], "env": { "AWS_PROFILE": "your-aws-profile", "AWS_REGION": "us-east-1", "FASTMCP_LOG_LEVEL": "ERROR" } }, "awslabs.bedrock-kb-retrieval-mcp-server": { "command": "uvx", "args": [ "awslabs.bedrock-kb-retrieval-mcp-server@latest" ], "env": { "AWS_PROFILE": "your-aws-profile", "AWS_REGION": "us-east-1", "FASTMCP_LOG_LEVEL": "ERROR" } }, "awslabs.cost-analysis-mcp-server": { "command": "uvx", "args": [ "awslabs.cost-analysis-mcp-server@latest" ], "env": { "AWS_PROFILE": "your-aws-profile", "FASTMCP_LOG_LEVEL": "ERROR" } }, "awslabs.cdk-mcp-server": { "command": "uvx", "args": [ "awslabs.cdk-mcp-server@latest" ], "env": { "FASTMCP_LOG_LEVEL": "ERROR" } }, "awslabs.aws-documentation-mcp-server": { "command": "uvx", "args": [ "awslabs.aws-documentation-mcp-server@latest" ], "env": { "FASTMCP_LOG_LEVEL": "ERROR" }, "disabled": false, "autoApprove": [] }, "awslabs.lambda-tool-mcp-server": { "command": "uvx", "args": [ "awslabs.lambda-tool-mcp-server@latest" ], "env": { "AWS_PROFILE": "your-aws-profile", "AWS_REGION": "us-east-1", "FUNCTION_PREFIX": "your-function-prefix", "FUNCTION_LIST": "your-first-function, your-second-function", "FUNCTION_TAG_KEY": "your-tag-key", "FUNCTION_TAG_VALUE": "your-tag-value" } }, "awslabs.terraform-mcp-server": { "command": "uvx", "args": [ "awslabs.terraform-mcp-server@latest" ], "env": { "FASTMCP_LOG_LEVEL": "ERROR" }, "disabled": false, "autoApprove": [] }, "awslabs.frontend-mcp-server": { "command": "uvx", "args": [ "awslabs.frontend-mcp-server@latest" ], "env": { "FASTMCP_LOG_LEVEL": "ERROR" }, "disabled": false, "autoApprove": [] }, "awslabs.valkey-mcp-server": { "command": "uvx", "args": [ "awslabs.valkey-mcp-server@latest" ], "env": { "VALKEY_HOST": "127.0.0.1", "VALKEY_PORT": "6379", "FASTMCP_LOG_LEVEL": "ERROR" }, "autoApprove": [], "disabled": false }, "awslabs.aws-location-mcp-server": { "command": "uvx", "args": [ "awslabs.aws-location-mcp-server@latest" ], "env": { "AWS_PROFILE": "your-aws-profile", "AWS_REGION": "us-east-1", "FASTMCP_LOG_LEVEL": "ERROR" }, "disabled": false, "autoApprove": [] }, "awslabs.memcached-mcp-server": { "command": "uvx", "args": [ "awslabs.memcached-mcp-server@latest" ], "env": { "MEMCACHED_HOST": "127.0.0.1", "MEMCACHED_PORT": "11211", "FASTMCP_LOG_LEVEL": "ERROR" }, "autoApprove": [], "disabled": false }, "awslabs.git-repo-research-mcp-server": { "command": "uvx", "args": [ "awslabs.git-repo-research-mcp-server@latest" ], "env": { "AWS_PROFILE": "your-aws-profile", "AWS_REGION": "us-east-1", "FASTMCP_LOG_LEVEL": "ERROR", "GITHUB_TOKEN": "your-github-token" }, "disabled": false, "autoApprove": [] }, "awslabs.cloudformation": { "command": "uvx", "args": [ "awslabs.cfn-mcp-server@latest" ], "env": { "AWS_PROFILE": "your-aws-profile" }, "disabled": false, "autoApprove": [] } } }

See individual server READMEs for specific requirements and configuration options.

If you have problems with MCP configuration or want to check if the appropriate parameters are in place, you can try the following:

# Run MCP server manually with timeout 15s $ timeout 15s uv tool run <MCP Name> <args> 2>&1 || echo "Command completed or timed out" # Example (Aurora MySQL MCP Server) $ timeout 15s uv tool run awslabs.mysql-mcp-server --resource_arn <Your Resource ARN> --secret_arn <Your Secret ARN> ... 2>&1 || echo "Command completed or timed out" # If the arguments are not set appropriately, you may see the following message: usage: awslabs.mysql-mcp-server [-h] --resource_arn RESOURCE_ARN --secret_arn SECRET_ARN --database DATABASE --region REGION --readonly READONLY awslabs.mysql-mcp-server: error: the following arguments are required: --resource_arn, --secret_arn, --database, --region, --readonly

Note about performance when usinguvx"@latest"suffix:

Using the"@latest"suffix checks and downloads the latest MCP server package from pypi every time you start your MCP clients, but it comes with a cost of increased initial load times. If you want to minimize the initial load time, remove"@latest"and manage your uv cache yourself using one of these approaches:

- uv cache clean <tool>: where {tool} is the mcp server you want to delete from cache and install again (e.g.: "awslabs.lambda-tool-mcp-server") (remember to remove the '').
- uvx <tool>@latest: this will refresh the tool with the latest version and add it to the uv cache.

This example uses docker with the "awslabs.nova-canvas-mcp-server and can be repeated for each MCP server

cd src/nova-canvas-mcp-server docker build -t awslabs/nova-canvas-mcp-server .

Optionally save sensitive environmental variables in a file:

# contents of a .env file with fictitious AWS temporary credentials AWS_ACCESS_KEY_ID=ASIAIOSFODNN7EXAMPLE AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY AWS_SESSION_TOKEN=AQoEXAMPLEH4aoAH0gNCAPy...truncated...zrkuWJOgQs8IZZaIv2BXIa2R4Olgk

Use the docker options:--env,--env-file, and--volumeas needed because the"env": {}are not available within the container.

{ "mcpServers": { "awslabs.nova-canvas-mcp-server": { "command": "docker", "args": [ "run", "--rm", "--interactive", "--env", "FASTMCP_LOG_LEVEL=ERROR", "--env", "AWS_REGION=us-east-1", "--env-file", "/full/path/to/.env", "--volume", "/full/path/to/.aws:/app/.aws", "awslabs/nova-canvas-mcp-server:latest" ], "env": {} } } }

Getting Started with Cline and Amazon Bedrock

IMPORTANT:Following these instructions may incur costs and are subject to theAmazon Bedrock Pricing. You are responsible for any associated costs. In addition to selecting the desired model in the Cline settings, ensure you have your selected model (e.g.anthropic.claude-3-7-sonnet) also enabled in Amazon Bedrock. For more information on this, seethese AWS docson enabling model access to Amazon Bedrock Foundation Models (FMs).
-

Follow the steps above in theInstallation and Setupsection to installuvfromAstral, install Python, and configure AWS credentials with the required services.