View a markdown version of this page

從 AgentCore 閘道接收進度通知 - Amazon Bedrock AgentCore
先決條件進度通知的運作方式程式碼範例

從 AgentCore 閘道接收進度通知

進度通知可讓 MCP 伺服器目標報告長時間執行工具呼叫的增量進度。當工具呼叫需要時間完成時，伺服器可以傳送notifications/progress事件，讓用戶端了解操作的狀態。AgentCore Gateway 會將這些通知從 MCP 伺服器目標轉送到您的用戶端，做為 Server-Sent Events (SSE) 區塊。

先決條件

若要從閘道接收進度通知：

  • 啟用回應串流 — 在開放連線期間，進度通知會以 SSE 區塊的形式傳送。在閘道的 true中streamingConfiguration.enableResponseStreaming將 設定為 protocolConfiguration.mcp。

  • MCP 伺服器目標類型 — 進度通知源自 MCP 伺服器目標。

  • 用戶端傳送Accept: text/event-stream標頭 — 用戶端必須請求 SSE 回應才能接收串流事件。

進度通知的運作方式

當用戶端在tools/call請求參數progressToken中使用 提出請求時，MCP 伺服器目標可以在執行期間傳送notifications/progress事件。在最終工具結果之前，閘道會以 SSE 區塊的形式將這些事件轉送至用戶端。

每個進度通知都包含：

  • progressToken — 符合原始請求中提供的字符。

  • progress — 目前的進度值 （數值）。

  • total — 指出完成目標的選用總值。

  • message — 目前狀態的選用人類可讀描述。

程式碼範例

範例
curl

  1. 使用進度字符呼叫工具：

    curl -N -X POST \
  https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -d '{
    "jsonrpc": "2.0",
    "id": "tool-call-1",
    "method": "tools/call",
    "params": {
      "name": "analyzeDataset",
      "arguments": {
        "datasetId": "ds-12345"
      },
      "_meta": {
        "progressToken": "progress-1"
      }
    }
}'

    閘道會傳回具有進度通知的 SSE 串流，後面接著最終結果：

    event: message
data: {"jsonrpc":"2.0","method":"notifications/progress","params":{"progressToken":"progress-1","progress":1,"total":4,"message":"Loading dataset..."}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/progress","params":{"progressToken":"progress-1","progress":2,"total":4,"message":"Running analysis..."}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/progress","params":{"progressToken":"progress-1","progress":3,"total":4,"message":"Generating report..."}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/progress","params":{"progressToken":"progress-1","progress":4,"total":4,"message":"Complete"}}

event: message
data: {"jsonrpc":"2.0","id":"tool-call-1","result":{"content":[{"type":"text","text":"Analysis complete. Found 3 anomalies in dataset ds-12345."}]}}
Python requests package

  1. import requests
import json
import sseclient

gateway_url = "https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp"
headers = {
    "Content-Type": "application/json",
    "Accept": "text/event-stream",
    "Authorization": "Bearer YOUR_ACCESS_TOKEN"
}

# Call tool with progress token (streaming response)
response = requests.post(gateway_url, headers=headers, json={
    "jsonrpc": "2.0",
    "id": "tool-call-1",
    "method": "tools/call",
    "params": {
        "name": "analyzeDataset",
        "arguments": {"datasetId": "ds-12345"},
        "_meta": {"progressToken": "progress-1"}
    }
}, stream=True)

# Process SSE events
client = sseclient.SSEClient(response)
for event in client.events():
    data = json.loads(event.data)
    if data.get("method") == "notifications/progress":
        params = data["params"]
        print(f"Progress: {params['progress']}/{params.get('total', '?')} - {params.get('message', '')}")
    elif "result" in data:
        print(f"Tool result: {data['result']}")
        break
MCP Client

  1. from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
import asyncio

async def progress_handler(progress_token, progress, total, message=None):
    """Handle progress notifications."""
    print(f"[{progress}/{total}] {message or ''}")

async def use_progress(url, token):
    headers = {"Authorization": f"Bearer {token}"}

    async with streamablehttp_client(url=url, headers=headers) as (
        read_stream, write_stream, _
    ):
        async with ClientSession(
            read_stream, write_stream,
            progress_handler=progress_handler
        ) as session:
            await session.initialize()

            # Call tool with progress token - notifications handled by callback
            result = await session.call_tool(
                name="analyzeDataset",
                arguments={"datasetId": "ds-12345"}
            )
            print(f"Tool result: {result}")
            return result

asyncio.run(use_progress(
    url="https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp",
    token="YOUR_ACCESS_TOKEN"
))
Strands MCP Client

  1. from mcp.client.streamable_http import streamablehttp_client
from strands import Agent
from strands.tools.mcp import MCPClient

mcp_url = "https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp"
access_token = "YOUR_ACCESS_TOKEN"

mcp_client = MCPClient(
    lambda: streamablehttp_client(
        mcp_url, headers={"Authorization": f"Bearer {access_token}"}
    )
)

# Strands handles streaming and progress notifications automatically
with mcp_client:
    agent = Agent(tools=mcp_client.list_tools_sync())
    response = agent("Analyze dataset ds-12345")
    print(response)