Skip to main content

GitHub Copilot Agent Tool calling -Safe by default

Through the MCP integration in GitHub Copilot, your AI agent is no longer limited to interactions with your IDE but can interact with your local computer and the outside world. A problem is that this open up a new range of possible attack vectors and malicious actors. So be careful when downloading a random MCP server example from the Internet.

GitHub Copilot Agents helps you by asking by default permission to execute a task:

Only by clicking on Continue the MCP server instance is called, and the tool is executed.

Of course, it can become annoying to confirm this over and over again. Therefore, you can choose between multiple options:

  • Allow in this Session
  • Allow in this Workspace
  • Always allow

This gives you full control to balance between security and convenience.

If you really want to just auto-approve everything (not recommended) set this in your settings:

chat.tools.autoApprove: true

Happy (vibe) coding!

More information

Use MCP servers in VS Code (Preview)

Extending Copilot Chat with the Model Context Protocol (MCP) - GitHub Docs

punkpeye/awesome-mcp-servers: A collection of MCP servers.

Labels:

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...
Read more

Azure DevOps/ GitHub emoji

I’m really bad at remembering emoji’s. So here is cheat sheet with all emoji’s that can be used in tools that support the github emoji markdown markup: All credits go to rcaviers who created this list.
Read more

VS Code Planning mode

After the introduction of Plan mode in Visual Studio , it now also found its way into VS Code. Planning mode, or as I like to call it 'Hannibal mode', extends GitHub Copilot's Agent Mode capabilities to handle larger, multi-step coding tasks with a structured approach. Instead of jumping straight into code generation, Planning mode creates a detailed execution plan. If you want more details, have a look at my previous post . Putting plan mode into action VS Code takes a different approach compared to Visual Studio when using plan mode. Instead of a configuration setting that you can activate but have limited control over, planning is available as a separate chat mode/agent: I like this approach better than how Visual Studio does it as you have explicit control when plan mode is activated. Instead of immediately diving into execution, the plan agent creates a plan and asks some follow up questions: You can further edit the plan by clicking on ‘Open in Editor’: ...
Read more