External Invocation

1. Activate Alibaba Cloud Model Studio

1. Create an account: If you do not have an Alibaba Cloud account, first register.

   If you encounter issues, see Create an Alibaba Cloud Account.

2. Activate Alibaba Cloud Model Studio: Sign in with your Alibaba Cloud account and go to Alibaba Cloud Model Studio. Read and accept the Terms of Service to automatically activate the service. If the Terms of Service do not appear, the service is already activated.

   If you see the message “You have not completed identity verification” when activating the service, you must complete identity verification first.

After your first activation of Model Studio, you receive a free quota for new users (valid for 90 days from activation). You can use it for model inference. For details and instructions on claiming the free quota, see the Free Quota for New Users page.

2. Get an Alibaba Cloud Model Studio API key

1. Open the API Key (China (Beijing)), API Key (Singapore), or API Key (US (Virginia)) page and click Create API Key.

2. Configure the following settings and click OK:

   • Owner Account: Select the Alibaba Cloud account (digit-only ID in the Account column).

   • Workspace: Select the default workspace.

3. Click next to the API key to copy it.

   Root accounts can view all API keys. RAM users can only view keys they created.

   

Integrate into a third-party application

Alibaba Cloud Model Studio supports configuring MCP services in Cherry Studio and Cursor. Both automatic and manual configuration methods are supported. The following example uses the Amap Maps service.

Develop integration using the SDK

You can use the MCP SDK to call Alibaba Cloud Model Studio MCP services. This provides full coding flexibility.

The following example builds an agent application that uses the Qwen Agent framework to call the Amap Maps MCP service and query today’s weather in Hangzhou.

1. Install the Qwen Agent framework.

   pip install -U "qwen-agent[gui,rag,code_interpreter,mcp]"

2. You can set your Alibaba Cloud Model Studio API key as an environment variable.

3. You can create a file named hangzhou_weather.py and use this sample code:

   Python

   # -*- coding: utf-8 -*-
   # Use the amap-maps tool to query Hangzhou weather
   
   import os
   from qwen_agent.agents import Assistant
   
   
   def query_hangzhou_weather():
       """Query today's weather in Hangzhou"""
       # Check environment variable
       api_key = os.getenv('DASHSCOPE_API_KEY')
       if not api_key:
           print("Error: Set the DASHSCOPE_API_KEY environment variable")
           print("Example: export DASHSCOPE_API_KEY=your_api_key")
           return
       
       llm_cfg = {'model': 'qwen-max'}
       system = (
           'You are a weather-query agent. You will use the amap-maps MCP service to get weather data.'
           'Always call the tool first to get structured weather data. Then give a brief summary.'
       )
       
       # Configure the MCP tool (Streamable HTTP protocol)
       tools = [{
           "mcpServers": {
               "amap-maps": {
                   "type": "streamable-http",
                   "url": "https://dashscope.aliyuncs.com/api/v1/mcps/amap-maps/mcp",
                   "headers": {
                       "Authorization": f"Bearer {api_key}"
                   }
               }
           }
       }]
       
       # Create the agent
       bot = Assistant(
           llm=llm_cfg,
           name='Weather Query Agent',
           description='Weather information lookup',
           system_message=system,
           function_list=tools,
       )
   
       # Query Hangzhou weather
       messages = []
       query = "What is today's date? What is the weather in Hangzhou today?"
       messages.append({'role': 'user', 'content': query})
   
       print("Querying today's weather in Hangzhou...")
       print("=" * 50)
       
       # Run the query and collect all responses
       all_responses = []
       for response in bot.run(messages):
           all_responses.append(response)
       
       # Extract the final assistant reply
       final_content = ""
       if all_responses:
           last_response = all_responses[-1]
           if isinstance(last_response, list):
               for item in last_response:
                   if isinstance(item, dict) and item.get('role') == 'assistant' and 'content' in item:
                       final_content = item['content']
           elif isinstance(last_response, dict) and 'content' in last_response:
               final_content = last_response['content']
       
       # Output the result
       if final_content:
           print(final_content)
       else:
           print("Failed to retrieve weather information")
   
   
   if __name__ == '__main__':
       query_hangzhou_weather()

4. You can run the code. The output appears as follows:

   

   If you run the code and receive the error message npx is not recognized as an internal or external command, first install <a href="https://nodejs.org/zh-cn" id="f9c77c8d95wkf">Node.js</a>.

What do I do if I cannot connect to an MCP service?

1. MCP service not enabled or not upgraded: Ensure the MCP service is enabled or upgraded in the Model Studio MCP Marketplace. See Enable an MCP service.

2. Invalid API key: Confirm that you are using a valid Alibaba Cloud Model Studio API key.

3. Quota exhausted: Some MCP services, such as web search, have monthly quotas. They stop automatically when the quota is exhausted.

For answers to common questions and information about other errors, see the FAQ.

The model responds normally and no MCP errors appear, but the MCP tool still does not run. What do I do?

The Large Language Model needs clear instructions to correctly call an MCP service. Specify the tool name and its capabilities in your prompt. For example, call the Alibaba Cloud Model Studio Amap Maps MCP service to plan a driving route from Hangzhou to Shanghai.