MCP

import os
from openai import OpenAI

client = OpenAI(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"（不建议）,
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 以下为华北2（北京）地域的URL，调用时请将 {WorkspaceId} 替换为真实的业务空间ID，各地域的URL不同。
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"
)

# MCP 工具配置
mcp_tool = {
    "type": "mcp",
    "server_protocol": "sse",
    "server_label": "WebParser",
    "server_description": "网页解析（WebParser）MCP 服务，一个专用于网页内容解析的工具包。",
    "server_url": "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/mcps/WebParser/sse",
    "headers": {
        "Authorization": "Bearer " + os.getenv("DASHSCOPE_API_KEY")
    }
}

response = client.responses.create(
    model="qwen3.8-max",
    input="https://help.aliyun.com/zh/model-studio/mcp 里支持哪些模型？",
    tools=[mcp_tool]
)

print("[模型回复]")
print(response.output_text)
print(f"\n[Token 用量] 输入: {response.usage.input_tokens}, 输出: {response.usage.output_tokens}, 合计: {response.usage.total_tokens}")

import os
from openai import OpenAI

client = OpenAI(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 以下为华北2（北京）地域的URL，调用时请将 {WorkspaceId} 替换为真实的业务空间ID，各地域的URL不同。
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"
)

mcp_tool = {
    "type": "mcp",
    "server_protocol": "sse",
    "server_label": "WebParser",
    "server_description": "网页解析（WebParser）MCP 服务，一个专用于网页内容解析的工具包。",
    "server_url": "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/mcps/WebParser/sse",
    "headers": {
        "Authorization": "Bearer " + os.getenv("DASHSCOPE_API_KEY")
    }
}

stream = client.responses.create(
    model="qwen3.8-max",
    input="https://help.aliyun.com/zh/model-studio/mcp 里支持哪些模型？",
    tools=[mcp_tool],
    stream=True
)

for event in stream:
    # 模型回复开始
    if event.type == "response.content_part.added":
        print("[模型回复]")
    # 流式文本输出
    elif event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)
    # 响应完成，输出用量
    elif event.type == "response.completed":
        usage = event.response.usage
        print(f"\n\n[Token 用量] 输入: {usage.input_tokens}, 输出: {usage.output_tokens}, 合计: {usage.total_tokens}")