Strands Agents SDK 入門 — MCP で外部ツールを接続する

エージェント → MCPClient → MCP サーバー
                              ↓
                         ツール一覧を返す
                              ↓
エージェント ← ツールとして登録 ← MCPClient

# uv がインストールされていない場合
curl -LsSf https://astral.sh/uv/install.sh | sh

from strands import Agent, tool
from strands.models import BedrockModel
from strands.tools.mcp import MCPClient
from mcp import stdio_client, StdioServerParameters
 
bedrock_model = BedrockModel(
    model_id="us.anthropic.claude-sonnet-4-20250514-v1:0",
    region_name="us-east-1",
)

mcp_client = MCPClient(lambda: stdio_client(
    StdioServerParameters(
        command="uvx",
        args=["awslabs.aws-documentation-mcp-server@latest"],
        env={"FASTMCP_LOG_LEVEL": "ERROR"},
    )
))
 
with mcp_client:
    tools = mcp_client.list_tools_sync()
    print(f"Available MCP tools: {[t.tool_name for t in tools]}")
 
    agent = Agent(model=bedrock_model, tools=tools)
    result = agent("What is Amazon Bedrock? Answer in 2 sentences.")

python -u mcp_basic.py

Available MCP tools: ['read_documentation', 'read_sections', 'search_documentation', 'recommend']

Tool #1: search_documentation
Tool #2: read_documentation
 
Amazon Bedrock is a fully managed service that provides secure, enterprise-grade
access to high-performing foundation models from leading AI companies, enabling
you to build and scale generative AI applications. The service supports 100+
foundation models from industry-leading providers including Amazon, Anthropic,
DeepSeek, Moonshot AI, MiniMax, and OpenAI, offering multiple API options for
integration.

Cycles: 3
Tools used: ['search_documentation', 'read_documentation']

@tool
def word_count(text: str) -> int:
    """Count the number of words in a text.
 
    Args:
        text: The text to count words in
 
    Returns:
        int: The number of words
    """
    return len(text.split())
 
mcp_client = MCPClient(lambda: stdio_client(
    StdioServerParameters(
        command="uvx",
        args=["awslabs.aws-documentation-mcp-server@latest"],
        env={"FASTMCP_LOG_LEVEL": "ERROR"},
    )
))
 
with mcp_client:
    mcp_tools = mcp_client.list_tools_sync()
    agent = Agent(model=bedrock_model, tools=mcp_tools + [word_count])
    result = agent(
        "Search AWS documentation for 'What is Amazon S3?' "
        "and count the words in the answer you give me."
    )

Tool #1: search_documentation
Tool #2: read_sections
Tool #3: read_documentation
Tool #4: word_count
 
The answer I provided contains 404 words explaining what Amazon S3 is, covering
its core functionality as an object storage service, how it works with buckets
and objects, the different types of buckets available, and its key features
including storage classes, management capabilities, security, data processing,
analytics, and consistency guarantees.

Cycles: 5
Tools used: ['search_documentation', 'read_sections', 'read_documentation', 'word_count']