Server facts
Open Source MCP Servers for AWS
Project
- Author
- awslabs
- Repository
- github.com/awslabs/mcp
- Website
- awslabs.github.io/mcp/
- License
- Apache-2.0
- Category
- Cloud & DevOps
Tech
- Runtime / language
- pythonPython
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 9,782
- Last commit
- Data as of
Tags
- Aws
- Cloud Infrastructure
- Developer Workflows
- Documentation
- Mcp Servers
Overview
Open Source MCP Servers for AWS is a collection of integrations that supply assistants with AWS-specific information and capabilities. The README organizes the suite around areas such as documentation, infrastructure, containers, serverless development, data services, AI, integration, and operations. It explains how servers can add service guidance and current reference material to a model's context, as well as turn cloud development workflows into callable operations. This is not a single generic MCP tool: users choose the relevant server for the task and configure that integration in their client. The supplied excerpt lists server offerings but does not provide individual tool identifiers.
The repository states that its servers are designed for stdio. It also notes that SSE was removed from the latest major versions and describes Streamable HTTP as work in progress. Separately, the README highlights managed AWS offerings, including an AWS MCP server and a knowledge service, so those should not be confused with every local server in this collection. Installation links target several popular clients. A prominent notice recommends the newer Agent Toolkit for AWS for production coding-agent and customer-agent development, while saying this repository still works and accepts contributions. Teams evaluating the suite should therefore consider the specific integration they need, the documented transport limits, and the relationship between these open-source projects and the newer toolkit.
Install & configure
Requirements
- An MCP-compatible client
- uvx for the documentation-server example
uvx awslabs.aws-documentation-mcp-server@latestThis is the AWS Documentation MCP Server configuration encoded in the README's installation link, not a command for the entire suite. The linked example uses ERROR logging and the aws documentation partition. Configure other servers separately; individual tool identifiers are not stated in the supplied excerpt.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp": {
"command": "uvx",
"args": [
"awslabs.aws-documentation-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "<desired logging level>",
"AWS_DOCUMENTATION_PARTITION": "<AWS documentation partition>"
}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp": {
"command": "uvx",
"args": [
"awslabs.aws-documentation-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "<desired logging level>",
"AWS_DOCUMENTATION_PARTITION": "<AWS documentation partition>"
}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"awslabs.aws-documentation-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "<desired logging level>",
"AWS_DOCUMENTATION_PARTITION": "<AWS documentation partition>"
}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp": {
"command": "uvx",
"args": [
"awslabs.aws-documentation-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "<desired logging level>",
"AWS_DOCUMENTATION_PARTITION": "<AWS documentation partition>"
}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"awslabs.aws-documentation-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "<desired logging level>",
"AWS_DOCUMENTATION_PARTITION": "<AWS documentation partition>"
}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
No individual tool names were confirmed in the source material. Check the repository for its current tool list.
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Provide an assistant with current AWS documentation and service guidance.
- Select specialized integrations for infrastructure and deployment workflows.
- Add AWS data and analytics context to an AI application.
- Explore cloud development automation through MCP-compatible clients.
Strengths
- Collects AWS-focused integrations across multiple cloud development areas.
- Organizes server choices by workload and working style.
- Offers Apache-2.0 licensed open-source projects alongside links to managed alternatives.
Limitations
- The repository describes local servers as stdio-only and removed SSE from current major versions.
- Production agent builders are directed toward the newer Agent Toolkit for AWS.
- A single universal tool catalog and launch command are not provided in the supplied excerpt.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
