Skip to main content
Glama

Strands Agent MCP

by imgaray

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:

  1. Server: The MCP server that exposes the agent execution API
  2. Registry: A simple registry for managing available agents
  3. 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:

  1. Clone the repository
  2. Create a virtual environment: python -m venv .venv
  3. Activate the virtual environment: source .venv/bin/activate (Linux/Mac) or .venv\Scripts\activate (Windows)
  4. 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
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

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.

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

  1. Overview
    1. Installation
      1. Usage
        1. Starting the MCP Server
        2. Creating Agent Plugins
        3. Using with Amazon Q
      2. Architecture
        1. Dependencies
          1. Development
            1. Creating a Test Plugin
              1. License

                Related MCP Servers

                • -
                  security
                  F
                  license
                  -
                  quality
                  A Model Context Protocol (MCP) server implementation for interacting with Phabricator API. This server allows LLMs to interact with Phabricator through a standardized interface.
                  Last updated -
                  5
                  Python
                • Amazon Web Services
                  aws-mcp

                  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
                  264
                  TypeScript
                  • Apple
                • A
                  security
                  A
                  license
                  A
                  quality
                  A Model Context Protocol (MCP) server implementation that provides EMQX MQTT broker interaction.
                  Last updated -
                  4
                  10
                  Python
                  Apache 2.0
                  • Apple
                • A
                  security
                  F
                  license
                  A
                  quality
                  A Model Context Protocol (MCP) server that interacts with system APIs, allowing users to check connections, search employees, register breakfast, and update chemical information by shifts.
                  Last updated -
                  21
                  37
                  JavaScript

                View all related MCP servers

                MCP directory API

                We provide all the information about MCP servers via our MCP API.

                curl -X GET 'https://glama.ai/api/mcp/v1/servers/imgaray/strands-agents-mcp'

                If you have feedback or need assistance with the MCP directory API, please join our Discord server