Yanked

This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Reason given by maintainers: load individual MCPs

Core MCP Server

MCP server that manages and coordinates other MCP servers in your environment

Features

Automatic MCP Server Management

Automatically installs and configures required MCP servers on startup
Ensures all necessary MCP servers are available
Maintains consistent configuration across servers

Planning and orchestration

Provides tools to plan and orchestrate AWS Labs MCP servers

UVX Installation Support

Provides tools to install MCP servers via UVX
Simplifies installation of additional MCP servers
Manages dependencies and version requirements

Centralized Configuration

Manages MCP server configurations in one place
Single configuration file for all servers
Automatic configuration validation

Environment Management

Handles environment variables and AWS credentials
Ensures proper AWS authentication
Manages environment variables across servers

Comprehensive Logging

Detailed logging for troubleshooting
Centralized logs for all servers
Configurable log levels

Prerequisites

Python 3.12 or higher
uv - Fast Python package installer and resolver
AWS credentials configured with Bedrock access
Node.js (for UVX installation support)

Environment Requirements

The server requires certain environment variables to be set for proper operation:

Required Environment Variables

MCP_CONFIG_PATH - Path to the MCP configuration file (e.g., /Users/username/Library/Application Support/vscode/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json)

Alternative Environment Variables

The server will also check for these alternative environment variables if MCP_CONFIG_PATH is not set:

CLINE_MCP_SETTINGS_PATH - Path to Cline MCP settings file
MCP_SETTINGS_PATH - Alternative path to MCP settings file

Setting Environment Variables

You can set these environment variables in your shell profile (e.g., ~/.zshrc or ~/.bashrc):

# Add to your shell profile
export MCP_CONFIG_PATH="/path/to/your/mcp/config.json"

Or you can set them when running the server:

MCP_CONFIG_PATH="/path/to/your/mcp/config.json" python -m mcp_core.server.server

AWS Environment Variables

For AWS services integration:

AWS_PROFILE - AWS profile to use for AWS services
AWS_REGION - AWS region to use for AWS services

Installation

Here are some ways you can work with MCP across AWS, and we'll be adding support to more products including Amazon Q Developer CLI soon: (e.g. for Amazon Q Developer CLI MCP, ~/.aws/amazonq/mcp.json):

{
  "mcpServers": {
    "awslabs.core-mcp-server": {
      "command": "uvx",
      "args": [
        "awslabs.core-mcp-server@latest"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "MCP_SETTINGS_PATH": "path to your mcp server settings"
      },
      "autoApprove": [],
      "disabled": false
    }
  }
}

Tools and Resources

The server exposes the following tools through the MCP interface:

prompt_understanding - Helps to provide clear plan for building AWS Solutions
install_awslabs_mcp_server - Installs MCP servers via UVX
update - Updates all MCP servers to ensure they are up-to-date with the latest configuration

Automatic Server Installation

The server automatically installs and configures required MCP servers on startup and before the server is started. This feature ensures that all necessary MCP servers are always available for use and up-to-date with the latest configuration, even when the server is restarted.

Configuration

The list of servers to be automatically installed is defined in mcp_core/server/available_servers.py. Each server entry includes:

"server-name": {
  "command": "uvx",  # Command to run the server
  "args": ["package-name"],  # Arguments for the command
  "env": {  # Environment variables
    "SHELL": "/usr/bin/zsh",
    "FASTMCP_LOG_LEVEL": "ERROR"
  },
  "disabled": False,  # Whether the server is disabled
  "autoApprove": []  # List of tools to auto-approve
}

Metadata

Release files for awslabs.core-mcp-server 0.0.2025141004

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for awslabs.core-mcp-server 0.0.2025141004
File	Size	Uploaded
awslabs_core_mcp_server-0.0.2025141004.tar.gz	50.4 kB	Apr 14, 2025	Details

Built distribution (wheel)

Table of built distributions (wheels) for awslabs.core-mcp-server 0.0.2025141004
File	Interpreter	ABI	Platform	Reset
awslabs_core_mcp_server-0.0.2025141004-py3-none-any.whl 18.2 kB Apr 14, 2025	Python 3	none	any	Details

Total release size: 68.6 kB

Release files / awslabs_core_mcp_server-0.0.2025141004.tar.gz

Download URL	awslabs_core_mcp_server-0.0.2025141004.tar.gz
Size	50.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`1492e94c9c6fbf68f007080a3cdc09d39b79d988077d684b02063256c3b7668c`
BLAKE2b-256 checksum How to use checksums	`aade84f01c6d969f263c8286ec0d497640b3496a0daf0a8dff33889ff95bc456`
Upload date	Apr 14, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/awslabs/mcp
Publishing commit: github.com/awslabs/mcp/tree/924451f2bea4997e9831057e629a448b7818937f

Workflow

Publishing configuration: github.com/awslabs/mcp/blob/924451f2bea4997e9831057e629a448b7818937f/.github/workflows/release.yml
Publishing logs: github.com/awslabs/mcp/actions/runs/14442929138/attempts/1

Artifact

Subject: awslabs_core_mcp_server-0.0.2025141004.tar.gz
SHA-256 checksum: 1492e94c9c6fbf68f007080a3cdc09d39b79d988077d684b02063256c3b7668c Verifying attestations

Release files / awslabs_core_mcp_server-0.0.2025141004-py3-none-any.whl

Download URL	awslabs_core_mcp_server-0.0.2025141004-py3-none-any.whl
Size	18.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`256f6f2f055145201a582d70acf72180891e324ddda2191d3a455e4678a968aa`
BLAKE2b-256 checksum How to use checksums	`732079bd0804555e12af594d94f317a96bf22cd944aaaecc4e18575a4bdc03c3`
Upload date	Apr 14, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/awslabs/mcp
Publishing commit: github.com/awslabs/mcp/tree/924451f2bea4997e9831057e629a448b7818937f

Workflow

Publishing configuration: github.com/awslabs/mcp/blob/924451f2bea4997e9831057e629a448b7818937f/.github/workflows/release.yml
Publishing logs: github.com/awslabs/mcp/actions/runs/14442929138/attempts/1

Artifact

Subject: awslabs_core_mcp_server-0.0.2025141004-py3-none-any.whl
SHA-256 checksum: 256f6f2f055145201a582d70acf72180891e324ddda2191d3a455e4678a968aa Verifying attestations