SDK Python

v1.0.0Coding Agentsstable

A model-driven approach to building AI agents in just a few lines of code.

agenticagentic-aiagentsaianthropic
Share:
5,915
Stars
0
Downloads
0
Weekly
0/5

What is SDK Python?

SDK Python is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model-driven approach to building ai agents in just a few lines of code.

A model-driven approach to building AI agents in just a few lines of code.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A model-driven approach to building AI agents in just a few

Use Cases

Model-driven agent building
Multi-LLM support
Rapid agent development
strands-agents

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx sdk-python

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use SDK Python

Strands Agents SDK is an open-source Python (and TypeScript) framework from AWS that takes a model-driven approach to building AI agents — you define tools and a model, and the SDK handles the agentic loop, tool calling, streaming, and multi-agent orchestration in just a few lines of code. It defaults to Amazon Bedrock as its model provider (supporting Claude Sonnet on Bedrock out of the box) and also integrates with Anthropic direct, OpenAI, Gemini, Ollama, and LiteLLM for local and third-party models. Developers use it to rapidly prototype and deploy production-grade AI agents with MCP support, structured output, guardrails, and event-driven observability.

Prerequisites

  • Python 3.10 or later (for the Python SDK)
  • Node.js 20 or later (for the TypeScript SDK)
  • AWS credentials configured with Bedrock model access enabled (default provider), OR an Anthropic/OpenAI/Gemini API key if using those providers instead
  • pip or uv for Python package installation
1

Install the Python SDK

Install the core strands-agents package and the optional built-in tools package. Python 3.10+ is required.

pip install strands-agents strands-agents-tools
2

Configure your model provider

By default Strands uses Amazon Bedrock. Ensure your AWS credentials are configured, or switch to a different provider by importing an alternate model provider class.

# Default: Amazon Bedrock (requires AWS credentials)
aws configure

# Or use Anthropic direct:
pip install anthropic
# then in code:
from strands.models.anthropic import AnthropicModel
model = AnthropicModel(model_id='claude-sonnet-4-6', api_key='sk-ant-...')
3

Create your first agent

Import Agent and pass a list of tools. The agent automatically handles the tool-calling loop until the task is complete.

from strands import Agent
from strands_tools import calculator

agent = Agent(tools=[calculator])
result = agent("What is the square root of 1764?")
print(result)
4

Connect an MCP server as a tool source

Strands natively supports MCP servers. Use MCPClient to connect and automatically load all tools from any MCP-compatible server.

from strands import Agent
from strands.tools.mcp import MCPClient

mcp_client = MCPClient(
    command='npx',
    args=['-y', '@wonderwhy-er/desktop-commander@latest']
)

with mcp_client:
    agent = Agent(tools=mcp_client.list_tools_sync())
    agent("Read the file at ~/project/main.py and summarise it")
5

Use the TypeScript SDK

For TypeScript projects, install the npm package and invoke the agent similarly.

npm install @strands-agents/sdk

// agent.ts
import { Agent } from '@strands-agents/sdk';
const agent = new Agent();
const result = await agent.invoke('What is the capital of France?');
console.log(result);

SDK Python Examples

Client configuration

Strands Agents SDK is a library you embed in your own code, not an MCP server. A typical Python script using the Anthropic provider directly looks like this:

from strands import Agent
from strands.models.anthropic import AnthropicModel
from strands_tools import file_read, shell

model = AnthropicModel(
    model_id='claude-sonnet-4-6',
    api_key='sk-ant-your-key-here'
)

agent = Agent(model=model, tools=[file_read, shell])
agent("List all Python files in the current directory")

Prompts to try

Example tasks well-suited to Strands agents with tool access.

- "Calculate the compound interest on $10,000 at 5% over 10 years"
- "Read the contents of config.yaml and validate all required keys are present"
- "Search the web for recent Python 3.13 release notes and summarise the new features"
- "Build a two-agent pipeline where one agent writes tests and another reviews them"

Troubleshooting SDK Python

NoCredentialsError when using the default Bedrock provider

Run `aws configure` to set up your AWS access key and secret, or set the AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_DEFAULT_REGION environment variables. Also ensure you have enabled model access for Claude Sonnet in the Bedrock console for your region.

ModuleNotFoundError: No module named 'strands_tools'

Install the tools package separately: `pip install strands-agents-tools`. It is a distinct package from the core SDK.

MCP tools not loading from MCPClient

Ensure the MCP server command runs successfully in your terminal before embedding it in MCPClient. The MCPClient context manager must remain open while the agent is running — do not call list_tools_sync outside the `with mcp_client:` block.

Frequently Asked Questions about SDK Python

What is SDK Python?

SDK Python is a Model Context Protocol (MCP) server that model-driven approach to building ai agents in just a few lines of code. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install SDK Python?

Follow the installation instructions on the SDK Python GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with SDK Python?

SDK Python works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is SDK Python free to use?

Yes, SDK Python is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "sdk-python": { "command": "npx", "args": ["-y", "sdk-python"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use SDK Python?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides