Strands Agent MCP

A Model Context Protocol (MCP) server for executing Strands agents. This project provides a simple way to integrate Strands agents with Amazon Q and other MCP-compatible systems.

IMPORTANT: This project is currently in alpha stage and not yet published on PyPI.

Overview

Strands Agent MCP is a bridge between the Strands agent framework and the Model Context Protocol (MCP). It allows you to:

Register Strands agents as MCP tools
Execute Strands agents through MCP
Find agents by specific skills

The project uses a plugin architecture that makes it easy to add new agents without modifying the core code.

Installation

Note: This package is not yet available on PyPI. You'll need to install it from source.

# Clone the repository
git clone https://github.com/yourusername/strands-agent-mcp.git
cd strands-agent-mcp

# Install the package
pip install -e .

Usage

Starting the MCP Server

strands-agent-mcp

This will start the MCP server.

Environment Variables

The server supports the following environment variables:

PLUGIN_PATH: Custom path to look for plugins (default: ".")
PLUGIN_NAMESPACE: Custom namespace prefix for plugins (default: 'sap_mcp_plugin')

Creating Agent Plugins

To create a new agent plugin, create a Python package with a name that starts with sap_mcp_plugin_ (sap stands for strands agent plugin). Your package should implement a build_agents function that returns a list of AgentEntry objects:

from typing import List
from boto3 import Session
from strands import Agent
from strands.models import BedrockModel

from strands_agent_mcp.registry import AgentEntry

def build_agents() -> List[AgentEntry]:
    return [
        AgentEntry(
            name="my-agent",
            agent=Agent(
                model=BedrockModel(boto_session=Session(region_name="us-west-2"))
            ),
            skills=["general-knowledge", "coding"]
        )
    ]

Using with Amazon Q

Once the MCP server is running, you can connect it to Amazon Q. Refer to the Amazon Q documentation for the correct connection parameters.

The following MCP tools will be available:

execute_agent: Execute an agent with parameters agent_name and prompt
list_agents: List all available agents

Architecture

The project consists of three main components:

Server: The MCP server that exposes the agent execution API
Registry: A registry for managing available agents and their skills
Plugins: Dynamically discovered modules that register agents with the registry

The server automatically discovers all installed plugins that follow the naming convention and registers their agents.

Dependencies

fastmcp>=2.3.4: For implementing the MCP server
strands-agents>=0.1.1: The core Strands agent framework
strands-agents-builder>=0.1.0: Tools for building Strands agents
strands-agents-tools>=0.1.0: Additional tools for Strands agents

Development

This project uses uv for dependency management. To set up a development environment:

Clone the repository
Install uv if you don't have it already: pip install uv
Create a virtual environment and install dependencies:
uv venv uv sync

Sample Plugin

The repository includes a sample plugin (sap_mcp_plugin_simple) that demonstrates how to create and register a simple agent:

from typing import List
from boto3 import Session
from strands import Agent
from strands.models import BedrockModel

from strands_agent_mcp.registry import AgentEntry

def build_agents() -> List[AgentEntry]:
    return [
        AgentEntry(
            name="simple-agent",
            agent=Agent(
                model=BedrockModel(boto_session=Session(region_name="us-west-2"))
            ),
            skills=["general-knowledge"]
        )
    ]

License

This project is licensed under the terms of the LICENSE file included in the repository.

Install Server

HTTP connection URL

security – no known vulnerabilities

license - permissive license

quality - confirmed to work

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Tools

A Model Context Protocol (MCP) server that enables integration of Strands agents with Amazon Q and other MCP-compatible systems through a plugin architecture.

Related MCP Servers

aws-mcp
RafalWilinski
A
security
F
license
A
quality
A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your AWS environment. This allows for natural language querying and management of your AWS resources during conversations. Think of better Amazon Q alternative.
Last updated -
3
282
TypeScript
Elasticsearch MCP Server
awesimon
A
security
A
license
A
quality
Connects agents to Elasticsearch data using the Model Context Protocol, allowing natural language interaction with Elasticsearch indices through MCP Clients like Claude Desktop and Cursor.
Last updated -
11
175
12
TypeScript
MIT License
Createve.AI Nexus
spgoodman
-
security
A
license
-
quality
An open-source implementation of the Model Context Protocol (MCP) that bridges AI agents with enterprise systems, enabling secure access to real-world data and capabilities.
Last updated -
2
Python
Apache 2.0
Google Research MCP
mixelpixx
-
security
A
license
-
quality
Model Context Protocol (MCP) server that provides AI assistants with advanced web research capabilities, including Google search integration, intelligent content extraction, and multi-source synthesis.
Last updated -
23
4
TypeScript
MIT License

View all related MCP servers