Skip to main content
Glama
deenesjakoruzh
imgaray

Strands Agent MCP

by imgaray
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

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.

Related MCP server: A2A Client MCP Server

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:

  1. Server: The MCP server that exposes the agent execution API

  2. Registry: A registry for managing available agents and their skills

  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>=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:

  1. Clone the repository

  2. Install uv if you don't have it already: pip install uv

  3. 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.

Available Tools

3 tools
execute_agentC

Execute an agent with a given prompt

ParametersJSON Schema
NameRequiredDescriptionDefault
agent_nameYesThe name of the agent to execute
promptYesThe prompt to execute the agent with

TDQS

C2.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('execute') but doesn't explain what execution involves (e.g., whether it runs a process, returns output, has side effects, requires permissions, or has rate limits). This leaves critical behavioral traits unspecified for a tool that likely performs a significant operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action and parameters, making it easy to parse quickly. Every word earns its place, adhering to best practices for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of executing an agent (likely a non-trivial operation), no annotations, and no output schema, the description is incomplete. It fails to explain what happens during execution, what the output might be, or any behavioral context, leaving significant gaps for an AI agent to understand and use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, clearly documenting both parameters ('agent_name' and 'prompt'). The description adds no additional meaning beyond what the schema provides, such as format examples or constraints. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Execute an agent with a given prompt' clearly states the verb ('execute') and resource ('agent'), but it's vague about what execution entails (e.g., running a task, generating a response). It doesn't differentiate from sibling tools like 'list_agents' or 'list_skills', which are read-only listing operations, but the distinction is implied rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing agent), exclusions, or how it relates to siblings like 'list_agents' for selecting an agent to execute. Usage is implied from the name and parameters but not explicitly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_agentsC

list all available agents

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states what the tool does ('list all available agents') without revealing any behavioral traits such as whether it's read-only, if it requires authentication, how results are returned (e.g., pagination, format), or any rate limits. This is a significant gap for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description 'list all available agents' is a single, efficient sentence that front-loads the core action and resource. It has zero waste, making it appropriately sized for a simple listing tool. Every word earns its place by conveying the essential purpose without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is minimal but incomplete. It lacks context about what 'agents' are, how the listing is structured (e.g., as a list, array, or paginated), and behavioral details. For a tool with no structured data to rely on, the description should provide more completeness to aid the agent effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and the schema description coverage is 100% (as there are no parameters to describe). The description doesn't need to add parameter semantics, so it meets the baseline of 4 for tools with no parameters. No additional value is required beyond stating the purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'list all available agents' clearly states the verb ('list') and resource ('agents'), making the purpose understandable. However, it lacks specificity about what 'agents' are in this context and doesn't distinguish from sibling tools like 'list_skills', which suggests a similar listing operation but for different resources. The description is functional but generic.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'execute_agent' (which likely performs actions with agents) or 'list_skills' (which lists a different resource), leaving the agent to infer usage based on tool names alone. There's no explicit context or exclusions provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_skillsB

list all available skills for agents

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool lists skills but doesn't describe behavioral traits such as whether it's read-only, requires authentication, has rate limits, or what the output format looks like. For a tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded, making it easy for an agent to parse quickly. Every part of the sentence earns its place by conveying essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no output schema), the description is minimal but adequate for basic understanding. However, it lacks context about behavioral aspects (e.g., read-only status, output format) and doesn't differentiate from siblings, making it incomplete for optimal agent guidance. With no annotations and no output schema, more detail would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and the schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics beyond what the schema provides. A baseline of 4 is appropriate as it avoids redundancy while being complete for a parameterless tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('list') and resource ('all available skills for agents'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from its siblings (execute_agent and list_agents), which would require a 5. The description avoids tautology by not merely restating the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus its siblings (execute_agent and list_agents) or any alternatives. It implies usage for retrieving skill information but lacks explicit context, prerequisites, or exclusions, leaving the agent with minimal direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observedexecute_agent
    • First observedlist_agents
    • First observedlist_skills
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: execute_agent runs an agent, list_agents enumerates available agents, and list_skills enumerates available skills. The descriptions make it unambiguous which tool to use for each operation.

Naming Consistency5/5

All three tools follow a consistent verb_noun pattern (execute_agent, list_agents, list_skills) with the same naming convention throughout. The verbs (execute, list) are appropriate and consistently applied.

Tool Count3/5

With only 3 tools, the set feels thin for an agent management system. While the tools cover basic operations (list and execute), there are likely missing capabilities like creating, updating, or deleting agents or skills, which limits the server's scope.

Completeness2/5

The tool surface is significantly incomplete for agent management. It lacks essential CRUD operations (e.g., create_agent, update_agent, delete_agent, create_skill) and other lifecycle actions (e.g., stop_agent, monitor_agent). This will cause agent failures when trying to perform basic management tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

  • Mercado PagoOAuth
    com.mercadopago.mcp

    The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.

    FinanceE-commerce & RetailApp Automation
    2
  • Remote MCPA
    com.remote-mcp.mcp

    The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.

    Developer ToolsSearchAgent Orchestration
    13
  • hithereiamaliff-mcp-nextcloudOAuth
    ai.smithery

    A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

    Cloud StorageFile SystemsWorkplace & Productivity
    237
  • ClawLinkOAuth
    dev.claw-link

    MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.

    App AutomationWorkplace & Productivity
    24

Related MCP Servers

  • OpenAI Agents MCP Server

    lroolle
    F
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server that enables Claude users to access specialized OpenAI agents (web search, file search, computer actions) and a multi-agent orchestrator through the MCP protocol.
    4
    10
    -

  • MCP Server Demo

    Drakoxw
    F
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server implementation that can be run directly or through Docker, enabling AI assistants to interact with external systems through the MCP standard.
    2
    -