how to connect to mcp using the qwen api - Alibaba Cloud Model Studio

Le Model Context Protocol (MCP) permet aux grands modèles de langage d'utiliser des outils et des données externes. Cette rubrique explique comment se connecter à un serveur MCP à l'aide de l'API Responses.

Utilisation

Lorsque vous utilisez l'API Responses, ajoutez les informations du serveur MCP dans le paramètre tools.

Récupérez l'endpoint Server-Sent Events (SSE) ainsi que les informations d'authentification du service MCP auprès de plateformes telles que ModelScope .

Prise en charge des serveurs MCP utilisant le protocole SSE.

10 serveurs MCP au maximum.

# 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)

Modèles pris en charge

Qwen-Max : séries Qwen3,8-Max et Qwen3,7-Max
Qwen-Plus : séries Qwen3,7-Plus, Qwen3,6-Plus et Qwen3,5-Plus
Qwen-Flash : séries Qwen3,7-Flash, Qwen3,6-Flash et Qwen3,5-Flash
Série open source Qwen3,8
Série open source Qwen3,6 (à l'exception de qwen3,6-27b)
Série open source Qwen3,5

Disponible uniquement via l'API Responses.

Prise en main

Cet exemple utilise le service MCP Fetch web scraping disponible sur ModelScope. Vous pouvez obtenir l'endpoint SSE et les informations d'authentification du service dans la section Service configuration située à droite.

Obtenez une clé API et configurez-la en tant que variable d'environnement.

Remplacez la valeur de server_url par l'endpoint SSE fourni par la plateforme du service MCP. Remplacez également les informations d'authentification dans headers par le jeton fourni par cette plateforme.

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"
        }
    ]
}'

Après exécution du code, la réponse suivante est renvoyée :

[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

Sortie en streaming

Les appels d'outils MCP peuvent impliquer plusieurs interactions avec des services externes. Activez le mode streaming pour recevoir les résultats intermédiaires en temps réel.

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
}'

Après exécution du code, la réponse suivante est renvoyée :

[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

Paramètres

L'outil mcp prend en charge les paramètres suivants :

Paramètre	Obligatoire	Description
`type`	Oui	Définissez la valeur sur `"mcp"`.
`server_protocol`	Oui	Protocole de communication avec le serveur MCP. Actuellement, seul le protocole `"sse"` est pris en charge.
`server_label`	Oui	Libellé du serveur MCP, utilisé pour identifier le service.
`server_description`	Non	Description des fonctionnalités du serveur MCP. Elle aide le modèle à comprendre les capacités et les cas d'utilisation du service. Il est recommandé de renseigner ce paramètre pour améliorer la précision des appels au modèle.
`server_url`	Oui	URL de l'endpoint du serveur MCP.
`headers`	Non	En-têtes de requête à inclure lors de la connexion au serveur MCP, tels que les informations d'authentification comme `Authorization`.

Exemple :

{
        "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"
    }

Facturation

La facturation comprend :

Frais d'inférence du modèle : facturés en fonction de l'utilisation des tokens par le modèle.
Frais du serveur MCP : soumis aux règles de facturation propres à chaque serveur MCP.