azure function hosting mcp server

Run the following command to create the azure function with mcp 

azd init --template remote-mcp-functions-python -e mcpserver-python

Once you have finish, go to the root folder where you will see pyproject.toml and azure.yaml, etc.

Then start vscode. Make sure you have the pre-requisites like Azure function Developer tool and azurite all setup. 

From vscode, select "Debug". It will prompt you to create a virtual environment. Please select "yes". When it ask you to run azurite - please select yes. 


Running the MCP function app

Next run the function app. You have to go into the src folder first and run vscode. 

Then you will be prompted to create an environment. Hit F5 or Run -> Debug. that will install your python modules under requirements.txt. 


Launch MCP Server

Next we will lanch our mcp server by creating a file call mcp.json.


{
    "inputs": [
        {
            "type": "promptString",
            "id": "functions-mcp-extension-system-key",
            "description": "Azure Functions MCP Extension System Key",
            "password": true
        },
        {
            "type": "promptString",
            "id": "functionapp-name",
            "description": "Azure Functions App Name"
        }
    ],
    "servers": {
        "remote-mcp-function": {
            "type": "http",
            "url": "https://${input:functionapp-name}.azurewebsites.net/runtime/webhooks/mcp",
            "headers": {
                "x-functions-key": "${input:functions-mcp-extension-system-key}"
            }
        },
        "local-mcp-function": {
            "type": "http",
            "url": "http://0.0.0.0:7071/runtime/webhooks/mcp"
        }
    }

} 

And you can see it here



Goto local-mcp-function and click "Run"



From the chat window, we issue a "say hello". Then the chatbot will ask for permission to use mcp tool.

Ensure you have configure the chatbox correctly. Ensure it is agent mode and then click on "Configure tools" you can see mcp-local-function, as shown here

Next we will configure the chatbox



And as you can see from here, we are able to hit the azure function mcp server hello_mcp function and it is also asking for permission.



And finally we can see the outputs:- 






Comments

Post a Comment

Popular posts from this blog

vllm : Failed to infer device type

Trying to run vllm without gpu will typicaly lands you into this issue. To resolve this issue: we can use set these both. Setting one does not work for me. So i had to configure both settings below:- 1.  environment variable CUDA_VISIBLE_DEVICES = "" 2. in the command line, change to use device cpu and remove  tensor-parallel-size. For example, python3 -m vllm.entrypoints.openai.api_server --port 8080 --model deepseek-ai/DeepSeek-R1 --device cpu --trust-remote-code --max-model-len 4096" References https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#failed-to-infer-device-type
Read more

NodeJS: Error: spawn EINVAL in window for node version 20.20 and 18.20

Encounter this issue when running autorest (that uses nodejs).  I am using node version:  v18.20.2 After i revert to use node v18.12.0, then i was able to get my app to run without this error. Since i am working with Azure devops yaml, i was able to use the following to resolve my issue.  - task : NodeTool@0   inputs :     versionSource : 'spec'     versionSpec : '18.18.0'
Read more

android studio kotlin source is null error

Image
This org.jetbrains.kotlin.util.FileAnalysisException with a java.lang.IllegalArgumentException: source must not be null is a known issue that can sometimes occur with the Kotlin compiler. It seems to be related to how the compiler analyzes certain source code structures. When this happens, you need to go clean your project and do another rebuild.  For my case, I was trying to test out the databinding = true feature. 
Read more