AWS AgentCore MCP Server

<div align="center"> <h1>AWS AgentCore MCP Server</h1> <h2>A comprehensive framework for building, securing, monitoring, and managing AI agents at scale</h2>

<div align="center"> <a href="https://github.com/aws/aws-agentcore-mcp-server/graphs/commit-activity"><img alt="GitHub commit activity" src="https://img.shields.io/github/commit-activity/m/aws/aws-agentcore-mcp-server"/></a> <a href="https://github.com/aws/aws-agentcore-mcp-server/issues"><img alt="GitHub open issues" src="https://img.shields.io/github/issues/aws/aws-agentcore-mcp-server"/></a> <a href="https://github.com/aws/aws-agentcore-mcp-server/pulls"><img alt="GitHub open pull requests" src="https://img.shields.io/github/issues-pr/aws/aws-agentcore-mcp-server"/></a> <a href="https://github.com/aws/aws-agentcore-mcp-server/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/aws/aws-agentcore-mcp-server"/></a> <a href="https://pypi.org/project/aws-agentcore-mcp-server/"><img alt="PyPI version" src="https://img.shields.io/pypi/v/aws-agentcore-mcp-server"/></a> <a href="https://python.org"><img alt="Python versions" src="https://img.shields.io/pypi/pyversions/aws-agentcore-mcp-server"/></a> </div>

<p> <a href="https://docs.aws.amazon.com/bedrock-agentcore/">Documentation</a> ◆ <a href="https://github.com/aws-samples/sample-amazon-bedrock-agentcore-onboarding">Samples</a> ◆ <a href="https://aws.github.io/bedrock-agentcore-starter-toolkit/">Starter Toolkit</a> ◆ <a href="https://github.com/aws/aws-agentcore-mcp-server">MCP Server</a> </p> </div>

This MCP server provides comprehensive documentation about AWS AgentCore to your GenAI tools, enabling you to build production-ready AI agents with enterprise-grade security, observability, and scalability.

What is AWS AgentCore?

AWS AgentCore is a comprehensive framework for building, securing, monitoring, and managing AI agents at scale on Amazon Bedrock. It provides:

• AgentCore Identity: Centralized management of agent identities and credentials
• AgentCore Gateway: Universal integration layer for APIs and external services
• AgentCore Observability: Advanced tracing, monitoring, and debugging capabilities
• AgentCore Code Interpreter: Secure code execution within sandboxed sessions
• AgentCore Memory: Short-term and long-term memory storage for context-aware agents

Prerequisites

The usage methods below require uv to be installed on your system. You can install it by following the official installation instructions.

Installation

You can use the AWS AgentCore MCP server with 40+ applications that support MCP servers, including Amazon Q Developer CLI, Anthropic Claude Code, Cline, and Cursor.

Q Developer CLI example

See the Q Developer CLI documentation for instructions on managing MCP configuration.

In ~/.aws/amazonq/mcp.json:

{
  "mcpServers": {
    "aws-agentcore": {
      "command": "uvx",
      "args": ["aws-agentcore-mcp-server"]
    }
  }
}

Claude Code example

See the Claude Code documentation for instructions on managing MCP servers.

claude mcp add aws-agentcore uvx aws-agentcore-mcp-server

Cline example

See the Cline documentation for instructions on managing MCP configuration.

Provide Cline with the following information:

I want to add the MCP server for AWS AgentCore.
Here's the GitHub link: @https://github.com/aws/aws-agentcore-mcp-server
Can you add it?

Cursor example

See the Cursor documentation for instructions on managing MCP configuration.

In ~/.cursor/mcp.json:

{
  "mcpServers": {
    "aws-agentcore": {
      "command": "uvx",
      "args": ["aws-agentcore-mcp-server"]
    }
  }
}

Available Tools

The MCP server provides the following documentation tools:

• quickstart() - Get started with AWS AgentCore SDK
• agentcore_identity() - Learn about secure agent authentication and authorization
• agentcore_gateway() - Integrate external APIs and services
• agentcore_observability() - Monitor and debug agents in production
• agentcore_code_interpreter() - Execute code securely in agents
• agentcore_memory() - Build context-aware agents with persistent memory
• agentcore_tools() - Integrate tools and extend agent capabilities

Quick Testing

You can quickly test the MCP server using the MCP Inspector:

npx @modelcontextprotocol/inspector uvx aws-agentcore-mcp-server

Note: This requires npx to be installed on your system. It comes bundled with Node.js.

The Inspector is also useful for troubleshooting MCP server issues as it provides detailed connection and protocol information. For an in-depth guide, have a look at the MCP Inspector documentation.

Server Development

git clone https://github.com/aws/aws-agentcore-mcp-server.git
cd aws-agentcore-mcp-server
python3 -m venv venv
source venv/bin/activate
pip3 install -e .

npx @modelcontextprotocol/inspector python -m aws_agentcore_mcp_server

Example Usage

Once installed, you can ask your AI assistant questions like:

• "How do I get started with AWS AgentCore?"
• "Show me how to set up AgentCore Identity for secure authentication"
• "How do I integrate external APIs using AgentCore Gateway?"
• "What observability features does AgentCore provide?"
• "How can I add code execution capabilities to my agent?"
• "How do I implement memory in my AgentCore agent?"
• "What tools can I integrate with my AgentCore agent?"

The MCP server will provide comprehensive documentation and code examples for each AgentCore component.

Contributing ❤️

We welcome contributions! See our Contributing Guide for details on:

• Reporting bugs & features
• Development setup
• Contributing via Pull Requests
• Code of Conduct
• Reporting of security issues

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Security

See CONTRIBUTING for more information.