从您的 AgentCore 网关接收日志消息

在工具执行期间，MCP 服务器目标可以使用该notifications/message方法向客户端发送日志消息。这些消息可以实时了解服务器正在做什么，对调试、审计和监控工具行为很有用。 AgentCore Gateway 将这些来自 MCP 服务器目标的日志通知作为 Server-Sent 事件 (SSE) 区块转发到您的客户端。

先决条件

要从您的网关接收日志消息，请执行以下操作：

启用响应流 -在打开的连接期间，日志消息作为 SSE 区块传输。streamingConfiguration.enableResponseStreaming在网关true中设置为protocolConfiguration.mcp。
MCP 服务器目标类型 -日志消息源自 MCP 服务器目标。
客户端发送标Accept头 -客户端必须发送，Accept: application/json, text/event-stream这样网关才能返回流式传输 (SSE) 响应。

日志级别

MCP 按严重性增加的顺序定义了以下日志级别：

级别	说明
`debug`	故障排除的详细诊断信息。
`info`	有关正常操作的一般信息性消息。
`notice`	正常但重要的事件。
`warning`	无法阻止操作的潜在危害情况。
`error`	阻止特定操作的错误情况。
`critical`	需要立即关注的危急情况。
`alert`	必须立即采取行动。
`emergency`	系统无法使用。

日志消息的工作原理

当 MCP 服务器目标notifications/message在工具执行期间发出时，网关会将其作为 SSE 事件转发给客户端。每条日志消息包括：

level— 消息的严重性级别。
logger— 标识源组件的可选名称。
data— 日志内容（字符串或结构化对象）。

日志消息是信息性的，不需要客户端的响应。它们与其他 SSE 事件（例如进度通知和最终工具结果）一起交付。

代码示例

例

curl (2025-11-25 and earlier)

调用工具并在 SSE 流中接收日志消息。将标MCP-Protocol-Version头设置为网关支持的版本。


curl -N -X POST \
  https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "MCP-Protocol-Version: 2025-11-25" \
  -d '{
    "jsonrpc": "2.0",
    "id": "tool-call-1",
    "method": "tools/call",
    "params": {
      "name": "deployService",
      "arguments": {
        "serviceName": "my-api",
        "environment": "staging"
      }
    }
}'

网关返回一个 SSE 流，其中包含日志消息，然后是最终结果：


event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"info","logger":"deploy-service","data":"Starting deployment of my-api to staging"}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"info","logger":"deploy-service","data":"Building container image..."}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"warning","logger":"deploy-service","data":"Deprecated configuration detected in service manifest"}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"info","logger":"deploy-service","data":"Deployment complete"}}

event: message
data: {"jsonrpc":"2.0","id":"tool-call-1","result":{"content":[{"type":"text","text":"Successfully deployed my-api to staging environment."}]}}

curl (2026-07-28)

在版本上2026-07-28，客户端通过设置_meta（该logging/setLevel操作在此版本io.modelcontextprotocol/logLevel中已停用）来选择为每个请求输入日志消息。服务器的发送量notifications/message仅达到或高于请求的级别。还包括Mcp-Method和Mcp-Name请求元数据标头以及_meta版本字段。标MCP-Protocol-Version题必须匹配_meta.io.modelcontextprotocol/protocolVersion。您的网关supportedVersions必须包括2026-07-28。


curl -N -X POST \
  https://mygateway-abcdefghij.gateway.bedrock-agentcore.us-west-2.amazonaws.com/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "MCP-Protocol-Version: 2026-07-28" \
  -H "Mcp-Method: tools/call" \
  -H "Mcp-Name: deployService" \
  -d '{
    "jsonrpc": "2.0",
    "id": "tool-call-1",
    "method": "tools/call",
    "params": {
      "name": "deployService",
      "arguments": {
        "serviceName": "my-api",
        "environment": "staging"
      },
      "_meta": {
        "io.modelcontextprotocol/protocolVersion": "2026-07-28",
        "io.modelcontextprotocol/clientInfo": {
          "name": "my-agent",
          "version": "1.0.0"
        },
        "io.modelcontextprotocol/clientCapabilities": {},
        "io.modelcontextprotocol/logLevel": "info"
      }
    }
}'

网关返回一个 SSE 流，其中包含日志消息，然后是最终结果：


event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"info","logger":"deploy-service","data":"Starting deployment of my-api to staging"}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"info","logger":"deploy-service","data":"Building container image..."}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"warning","logger":"deploy-service","data":"Deprecated configuration detected in service manifest"}}

event: message
data: {"jsonrpc":"2.0","method":"notifications/message","params":{"level":"info","logger":"deploy-service","data":"Deployment complete"}}

event: message
data: {"jsonrpc":"2.0","id":"tool-call-1","result":{"content":[{"type":"text","text":"Successfully deployed my-api to staging environment."}]}}

Python requests package (2025-11-25 and earlier)

将标MCP-Protocol-Version头设置为网关支持的版本。


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": "application/json, text/event-stream",
    "Authorization": "Bearer YOUR_ACCESS_TOKEN",
    "MCP-Protocol-Version": "2025-11-25"
}

# Call tool (streaming response)
response = requests.post(gateway_url, headers=headers, json={
    "jsonrpc": "2.0",
    "id": "tool-call-1",
    "method": "tools/call",
    "params": {
        "name": "deployService",
        "arguments": {"serviceName": "my-api", "environment": "staging"}
    }
}, stream=True)

# Process SSE events
client = sseclient.SSEClient(response)
for event in client.events():
    data = json.loads(event.data)
    if data.get("method") == "notifications/message":
        params = data["params"]
        print(f"[{params['level'].upper()}] {params.get('logger', '')}: {params['data']}")
    elif "result" in data:
        print(f"Tool result: {data['result']}")
        break

Python requests package (2026-07-28)

在版本上2026-07-28，通过设置io.modelcontextprotocol/logLevel来选择接收日志消息_meta（该logging/setLevel操作在此版本中已停用）。还要添加MCP-Protocol-VersionMcp-Method、和Mcp-Name标题以及_meta版本字段。您的网关supportedVersions必须包括2026-07-28。


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": "application/json, text/event-stream",
    "Authorization": "Bearer YOUR_ACCESS_TOKEN",
    "MCP-Protocol-Version": "2026-07-28",
    "Mcp-Method": "tools/call",
    "Mcp-Name": "deployService"
}

# Call tool (streaming response)
response = requests.post(gateway_url, headers=headers, json={
    "jsonrpc": "2.0",
    "id": "tool-call-1",
    "method": "tools/call",
    "params": {
        "name": "deployService",
        "arguments": {"serviceName": "my-api", "environment": "staging"},
        "_meta": {
            "io.modelcontextprotocol/protocolVersion": "2026-07-28",
            "io.modelcontextprotocol/clientInfo": {"name": "my-agent", "version": "1.0.0"},
            "io.modelcontextprotocol/clientCapabilities": {},
            "io.modelcontextprotocol/logLevel": "info"
        }
    }
}, stream=True)

# Process SSE events
client = sseclient.SSEClient(response)
for event in client.events():
    data = json.loads(event.data)
    if data.get("method") == "notifications/message":
        params = data["params"]
        print(f"[{params['level'].upper()}] {params.get('logger', '')}: {params['data']}")
    elif "result" in data:
        print(f"Tool result: {data['result']}")
        break

MCP Client


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

async def log_handler(level, logger, data):
    """Handle log messages from the server."""
    print(f"[{level.upper()}] {logger or 'server'}: {data}")

async def use_logging(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,
            logging_handler=log_handler
        ) as session:
            await session.initialize()

            # Call tool - log messages handled by callback
            result = await session.call_tool(
                name="deployService",
                arguments={"serviceName": "my-api", "environment": "staging"}
            )
            print(f"Tool result: {result}")
            return result

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

Strands MCP Client


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 log messages automatically
with mcp_client:
    agent = Agent(tools=mcp_client.list_tools_sync())
    response = agent("Deploy my-api to staging")
    print(response)

Javascript 在您的浏览器中被禁用或不可用。

要使用 Amazon Web Services 文档，必须启用 Javascript。请参阅浏览器的帮助页面以了解相关说明。

文档惯例

进度通知

采样