how to connect to mcp using the qwen api - Alibaba Cloud Model Studio: Central de Documentação do Alibaba Cloud

O Model Context Protocol (MCP) permite que modelos de linguagem de grande porte utilizem ferramentas e dados externos. Este tópico descreve como se conectar ao MCP usando a Responses API.

Uso

Adicione as informações do servidor MCP no parâmetro tools ao utilizar a Responses API.

Obtenha o endpoint de Server-Sent Events (SSE) e as informações de autenticação do service MCP em plataformas como ModelScope .

Compatível com servidores MCP que utilizam o protocolo SSE.

Limite de 10 servidores MCP.

# Import dependencies and create a client...
mcp_tool = {
    "type": "mcp",
    "server_protocol": "sse",
    "server_label": "my-mcp-service",
    "server_description": "A description of the MCP server's features to help the model understand its use cases.",
    "server_url": "https://your-mcp-server-endpoint/sse",
    "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
    }
}

response = client.responses.create(
    model="qwen3.8-max",
    input="Your question...",
    tools=[mcp_tool]
)

print(response.output_text)

Modelos suportados

Qwen-Max: séries Qwen3.8-Max e Qwen3.7-Max
Qwen-Plus: séries Qwen3.7-Plus, Qwen3.6-Plus e Qwen3.5-Plus
Qwen-Flash: séries Qwen3.7-Flash, Qwen3.6-Flash e Qwen3.5-Flash
Série open source Qwen3.8
Série open source Qwen3.6 (exceto qwen3.6-27b)
Série open source Qwen3.5

Disponível apenas por meio da Responses API.

Primeiros passos

Este exemplo utiliza o service MCP de web scraping Fetch do ModelScope. Você pode obter o SSE Endpoint e as informações de autenticação do service na seção Service configuration, à direita.

Obtenha um API key e configure it as an environment variable.

Substitua server_url pelo endpoint SSE da plataforma de service MCP. Substitua a autenticação em headers pelo token fornecido por essa plataforma.

python

import os
from openai import OpenAI

client = OpenAI(
    # If no environment variable, use: api_key="sk-xxx" (not recommended).
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

# MCP tool configuration
# Replace server_url with the SSE Endpoint that you got from a platform such as ModelScope
# If authentication is required, add the token from the corresponding platform to the headers
mcp_tool = {
    "type": "mcp",
    "server_protocol": "sse",
    "server_label": "fetch",
    "server_description": "Fetch MCP Server that provides web scraping capabilities. It can scrape the content of a specified URL and return it as text.",
    "server_url": "https://mcp.api-inference.modelscope.net/xxx/sse",
}

response = client.responses.create(
    model="qwen3.8-max",
    input="https://news.aibase.com/zh/news, what is the AI news today?",
    tools=[mcp_tool]
)

print("[Model Response]")
print(response.output_text)
print(f"\n[Token Usage] Input: {response.usage.input_tokens}, Output: {response.usage.output_tokens}, Total: {response.usage.total_tokens}")

javascript

import OpenAI from "openai";
import process from 'process';

const openai = new OpenAI({
    // If no environment variable, use: apiKey: "sk-xxx" (not recommended).
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    // MCP tool configuration
    // Replace server_url with the SSE Endpoint that you got from a platform such as ModelScope
    // If authentication is required, add the token from the corresponding platform to the headers
    const mcpTool = {
        type: "mcp",
        server_protocol: "sse",
        server_label: "fetch",
        server_description: "Fetch MCP Server that provides web scraping capabilities. It can scrape the content of a specified URL and return it as text.",
        server_url: "https://mcp.api-inference.modelscope.net/xxx/sse",
    };

    const response = await openai.responses.create({
        model: "qwen3.8-max",
        input: "https://news.aibase.com/zh/news, what is the AI news today?",
        tools: [mcpTool]
    });

    console.log("[Model Response]");
    console.log(response.output_text);
    console.log(`\n[Token Usage] Input: ${response.usage.input_tokens}, Output: ${response.usage.output_tokens}, Total: ${response.usage.total_tokens}`);
}

main();

bash

# Replace server_url with the SSE Endpoint that you got from a platform such as ModelScope
# If authentication is required, add the token from the corresponding platform to the headers
# The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.8-max",
    "input": "https://news.aibase.com/zh/news, what is the AI news today?",
    "tools": [
        {
            "type": "mcp",
            "server_protocol": "sse",
            "server_label": "fetch",
            "server_description": "Fetch MCP Server that provides web scraping capabilities. It can scrape the content of a specified URL and return it as text.",
            "server_url": "https://mcp.api-inference.modelscope.net/xxx/sse"
        }
    ]
}'

Após executar o código, a seguinte resposta é retornada:

[Model Response]
Based on the documentation for the Model Context Protocol (MCP) on the Alibaba Cloud Model Studio (Bailian) help center, the supported models are:

*   Qwen Max:
    *   Qwen3.8-Max series
    *   Qwen3.7-Max series
*   Qwen Plus:
    *   Qwen3.7-Plus series
    *   Qwen3.6-Plus series
    *   Qwen3.5-Plus series
*   Qwen Flash:
    *   Qwen3.7-Flash series
    *   Qwen3.6-Flash series
    *   Qwen3.5-Flash series
*   Qwen3.6 Open Source Series (excluding qwen3.6-27b)
*   Qwen3.5 Open Source Series

Note: The documentation specifies that MCP is only supported via the Responses API (client.responses.create) and not the standard Chat Completions API.

[Token Usage] Input: 20583, Output: 1638, Total: 22221

Saída em streaming

Chamadas de ferramentas MCP podem envolver múltiplas interações com services externos. Ative o streaming para obter resultados intermediários em tempo real.

python

import os
from openai import OpenAI

client = OpenAI(
    # If no environment variable, use: api_key="sk-xxx" (not recommended).
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

# Replace server_url with the SSE Endpoint that you got from a platform such as ModelScope
# If authentication is required, add the token from the corresponding platform to the headers
mcp_tool = {
    "type": "mcp",
    "server_protocol": "sse",
    "server_label": "fetch",
    "server_description": "Fetch MCP Server that provides web scraping capabilities. It can scrape the content of a specified URL and return it as text.",
    "server_url": "https://mcp.api-inference.modelscope.net/xxx/sse",
}

stream = client.responses.create(
    model="qwen3.8-max",
    input="https://news.aibase.com/zh/news, what is the AI news today?",
    tools=[mcp_tool],
    stream=True
)

for event in stream:
    # The model response starts
    if event.type == "response.content_part.added":
        print("[Model Response]")
    # Streaming text output
    elif event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)
    # The response is complete, output the usage
    elif event.type == "response.completed":
        usage = event.response.usage
        print(f"\n\n[Token Usage] Input: {usage.input_tokens}, Output: {usage.output_tokens}, Total: {usage.total_tokens}")

javascript

import OpenAI from "openai";
import process from 'process';

const openai = new OpenAI({
    // If no environment variable, use: apiKey: "sk-xxx" (not recommended).
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    // Replace server_url with the SSE Endpoint that you got from a platform such as ModelScope
    // If authentication is required, add the token from the corresponding platform to the headers
    const mcpTool = {
        type: "mcp",
        server_protocol: "sse",
        server_label: "fetch",
        server_description": "Fetch MCP Server that provides web scraping capabilities. It can scrape the content of a specified URL and return it as text.",
        server_url": "https://mcp.api-inference.modelscope.net/xxx/sse",
    };

    const stream = await openai.responses.create({
        model: "qwen3.8-max",
        input: "https://news.aibase.com/zh/news, what is the AI news today?",
        tools: [mcpTool],
        stream: true
    });

    for await (const event of stream) {
        // The model response starts
        if (event.type === "response.content_part.added") {
            console.log("[Model Response]");
        }
        // Streaming text output
        else if (event.type === "response.output_text.delta") {
            process.stdout.write(event.delta);
        }
        // The response is complete, output the usage
        else if (event.type === "response.completed") {
            const usage = event.response.usage;
            console.log(`\n\n[Token Usage] Input: ${usage.input_tokens}, Output: ${usage.output_tokens}, Total: ${usage.total_tokens}`);
        }
    }
}

main();

bash

# Replace server_url with the SSE Endpoint that you got from a platform such as ModelScope
# If authentication is required, add the token from the corresponding platform to the headers
# The following URL is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.8-max",
    "input": "https://news.aibase.com/zh/news, what is the AI news today?",
    "tools": [
        {
            "type": "mcp",
            "server_protocol": "sse",
            "server_label": "fetch",
            "server_description": "Fetch MCP Server that provides web scraping capabilities. It can scrape the content of a specified URL and return it as text.",
            "server_url": "https://mcp.api-inference.modelscope.net/xxx/sse"
        }
    ],
    "stream": true
}'

Após executar o código, a seguinte resposta é retornada:

[Model Response]
Based on the documentation page for MCP on Alibaba Cloud Model Studio, the following models are supported:

*   Qwen Max Series: Qwen3.8-Max series and Qwen3.7-Max series
*   Qwen Plus Series: Qwen3.7-Plus series, Qwen3.6-Plus series and Qwen3.5-Plus series
*   Qwen Flash Series: Qwen3.7-Flash series, Qwen3.6-Flash series and Qwen3.5-Flash series
*   Qwen3.6 Open Source Series (excluding qwen3.6-27b)
*   Qwen3.5 Open Source Series

Note: These models support MCP functionality only via the Responses API.

[Token Usage] Input: 20472, Output: 945, Total: 21417

Parâmetros

A ferramenta mcp aceita os seguintes parâmetros:

Parâmetro	Obrigatório	Descrição
`type`	Sim	Defina como `"mcp"`.
`server_protocol`	Sim	Protocolo de comunicação com o servidor MCP. Atualmente, apenas `"sse"` é suportado.
`server_label`	Sim	Nome do rótulo do servidor MCP, utilizado para identificar o service.
`server_description`	Não	Descrição dos recursos do servidor MCP. Isso ajuda o modelo a compreender as capacidades e os cenários de uso do service. Recomendamos preencher este parâmetro para melhorar a precisão das chamadas do modelo.
`server_url`	Sim	URL do endpoint do servidor MCP.
`headers`	Não	Cabeçalhos de requisição a serem incluídos na conexão com o servidor MCP, como informações de autenticação, por exemplo, `Authorization`.

Exemplo:

{
        "type": "mcp",
        "server_protocol": "sse",
        "server_label": "fetch",
        "server_description": "Fetch MCP Server that provides web scraping capabilities. It can scrape the content of a specified URL and return it as text.",
        "server_url": "https://mcp.api-inference.modelscope.net/xxx/sse"
    }

Faturamento

O faturamento inclui:

Taxas de inferência do modelo: Cobradas com base no uso de tokens do modelo.
Taxas do servidor MCP: Sujeitas às regras de faturamento de cada servidor MCP.