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.

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
Discover and list available agents

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

Installation

pip install strands-agent-mcp

Usage

Starting the MCP Server

strands-agent-mcp

This will start the MCP server on the default port.

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 register_plugin function that registers one or more agents with the provided registry:

from strands import Agent
from strands.models import BedrockModel
from strands_agent_mcp.registry import Registry

def register_plugin(registry: Registry) -> None:
    registry.register("my-agent", Agent(
        model=BedrockModel(boto_session=Session(region_name="us-west-2")))
    )

Using with Amazon Q

Once the MCP server is running, you can use the agents with Amazon Q:

q chat --mcp-server http://localhost:8000

Then you can use the following commands in your chat:

List available agents: strands___list_agents
Execute an agent: strands___execute_agent with parameters agent (agent name) and prompt (the prompt to send to the agent)

Architecture

The project consists of three main components:

Server: The MCP server that exposes the agent execution API
Registry: A simple registry for managing available agents
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: For implementing the MCP server
strands-agents: The core Strands agent framework
strands-agents-builder: Tools for building Strands agents
strands-agents-tools: Additional tools for Strands agents

Development

To set up a development environment:

Clone the repository
Create a virtual environment: python -m venv .venv
Activate the virtual environment: source .venv/bin/activate (Linux/Mac) or .venv\Scripts\activate (Windows)
Install development dependencies: pip install -e ".[dev]"

Creating a Test Plugin

The repository includes a sample plugin (sap_mcp_plugin_test) that demonstrates how to create and register a simple agent called "simple-agent":

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

from strands_agent_mcp.registry import Registry


def register_plugin(registry: Registry) -> None:
    registry.register("simple-agent", Agent(
        model=BedrockModel(boto_session=Session(region_name="us-west-2")))
    )

License

[Add license information here]

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
280
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
35
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 -
1
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 -
27
2
TypeScript
MIT License

View all related MCP servers

Strands Agent MCP