Use MCP servers in VS Code

Model Context Protocol (MCP) is an open standard that lets AI models use external tools and services through a unified interface. In VS Code, MCP servers provide tools for tasks like file operations, databases, or interacting with external APIs.

MCP servers are one of three ways to extend chat with tools in VS Code, alongside built-in tools and extension-contributed tools. Learn more about types of tools.

This article guides you through setting up MCP servers and using their tools in Visual Studio Code. Beyond tools, MCP servers can also provide resources, prompts, and interactive apps.

Get started

Prerequisites

• Install the latest version of Visual Studio Code
• Access to Copilot

Add an MCP server

When you install an MCP server, you can choose to install it in your user profile or in the current workspace. The workspace configuration is stored in a .vscode/mcp.json file. Include in source control to share the same MCP server configuration with your team.

Add an MCP server from the MCP server gallery

The Extensions view contains an MCP server gallery to help you discover and install MCP servers from within VS Code. The gallery lists MCP servers from the GitHub MCP server registry.

To install an MCP server from the Extensions view:

1. Open the Extensions view (⇧⌘X (Windows, Linux Ctrl+Shift+X)) and enter @mcp in the search field to show the list of MCP servers.

2. To install an MCP server:

   • In your user profile: select Install

   • In your workspace: right-click the MCP server and select Install in Workspace (this updates the .vscode/mcp.json file in your workspace)

3. To view the MCP server details, select the MCP server in the list to open the details page.

Other options to add an MCP server

You have several other options to add an MCP server in VS Code:

{
  "image": "mcr.microsoft.com/devcontainers/typescript-node:latest",
  "customizations": {
    "vscode": {
      "mcp": {
        "servers": {
          "playwright": {
            "command": "npx",
            "args": ["-y", "@microsoft/mcp-server-playwright"]
          }
        }
      }
    }
  }
}

code --add-mcp "{\"name\":\"my-server\",\"command\": \"uvx\",\"args\": [\"mcp-server-fetch\"]}"

Configuration format

MCP server configuration is saved in the mcp.json JSON file (mcp.json).

Configuration structure

The configuration file has two main sections:

• "servers": {}: contains the list of MCP servers and their configurations - depending on the server type, different fields are required.

• "inputs": []: optional placeholders for sensitive information like API keys.

You can use predefined variables in the server configuration, for example to refer to the workspace folder (${workspaceFolder}).

Standard I/O (stdio) servers

Use this configuration for servers that communicate through standard input and output streams. This is the most common type for locally-run MCP servers.

{
  "servers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-memory"]
    }
  }
}

HTTP and Server-Sent Events (SSE) servers

Use this configuration for servers that communicate over HTTP. VS Code first tries the HTTP Stream transport and falls back to SSE if HTTP is not supported.

In addition to servers available over the network, VS Code can connect to MCP servers listening for HTTP traffic on Unix sockets or Windows named pipes by specifying the socket or pipe path in the form unix:///path/to/server.sock or pipe:///pipe/named-pipe on Windows. You can specify subpaths by using a URL fragment, such as unix:///tmp/server.sock#/mcp/subpath.

{
  "servers": {
    "context7": {
      "type": "http",
      "url": "https://mcp.context7.com/mcp"
    }
  }
}

Input variables for sensitive data

Input variables let you define placeholders for configuration values, avoiding the need to hardcode sensitive information like API keys or passwords directly in the server configuration.

When you reference an input variable using ${input:variable-id}, VS Code prompts you for the value when the server starts for the first time. The value is then securely stored for subsequent use. Learn more about input variables in VS Code.

Input variable properties:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "perplexity-key",
      "description": "Perplexity API Key",
      "password": true
    }
  ],
  "servers": {
    "perplexity": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "server-perplexity-ask"],
      "env": {
        "PERPLEXITY_API_KEY": "${input:perplexity-key}"
      }
    }
  }
}

Server naming conventions

When defining MCP servers, follow these naming conventions for the server name:

• Use camelCase for the server name, such as "uiTesting" or "githubIntegration"
• Avoid using whitespace or special characters
• Use a unique name for each server to avoid conflicts
• Use a descriptive name that reflects the server's functionality or brand, such as "github" or "database"

Use MCP tools in chat

After adding an MCP server, you can use the tools it provides in chat. MCP tools work like other tools in VS Code: they can be automatically invoked when using agents or explicitly referenced in your prompts.

To use MCP tools in chat:

1. Open the tool picker in the Chat view to select which tools the agent is allowed to use. MCP tools are grouped per MCP server.

2. Tools are automatically invoked based on the tool description and the task at hand. For example, install the GitHub MCP server and then ask "List my GitHub issues".

3. You can directly reference MCP tools in your prompt by typing # followed by the tool name.

Learn more about using tools in chat, including how to manage tool approvals, use the tool picker, and create tool sets.

Group related tools in a tool set

As you add more MCP servers, the list of tools can become long. You can group related tools into a tool set to make them easier to manage and reference.

Learn more about how to create and use tool sets.

Clear cached MCP tools

When VS Code starts the MCP server for the first time, it discovers the server's capabilities and tools. You can then use these tools in chat. VS Code caches the list of tools for an MCP server. To clear the cached tools, use the MCP: Reset Cached Tools command in the Command Palette.

Other MCP capabilities

Beyond tools, MCP servers can also provide resources for context, prompts for common tasks, and interactive apps.

Use MCP resources

MCP servers can give direct access to resources that you can use as context in your chat prompts. For example, a file system MCP server can let you access files and directories, or a database MCP server might provide access to database tables.

To add a resource from an MCP server to your chat prompt:

1. In the Chat view, select Add Context > MCP Resources

2. Select a resource type from the list and provide optional resource input parameters.

To view the list of available resources for an MCP server, use the MCP: Browse Resources command or use the MCP: List Servers > Browse Resources command to view resources for a specific server.

Use MCP prompts

MCP servers can provide preconfigured prompts for common tasks that you can invoke in chat with a slash command. To invoke an MCP prompt in chat, type / in the chat input field, followed by the prompt name, formatted as mcp.servername.promptname. Optionally, the MCP prompt might ask you for extra input parameters.

Use MCP Apps

MCP Apps enable MCP tools to return interactive UI components that render directly in chat. Instead of text-only responses, tools can display drag-and-drop lists, visualizations, forms, and other interactive elements. When an MCP server supports apps, the UI appears inline in the chat conversation so you can interact with it to complete tasks more efficiently.

Learn more about MCP Apps support in VS Code in our blog post.

Manage MCP servers

VS Code provides several options to discover, configure, and manage your MCP servers.

Manage installed MCP servers

You can perform various actions on the installed MCP servers, such as starting or stopping a server, viewing the server logs, uninstalling the server, and more.

To perform these actions on an MCP server, use either of these options:

• In the Extensions view, right-click a server in the MCP SERVERS - INSTALLED section or select the gear icon.

  

• Open the mcp.json configuration file and access the inline actions in the editor (code lenses).

  

  Use the MCP: Open User Configuration or MCP: Open Workspace Folder Configuration commands to access the MCP server configuration.

• Run the MCP: List Servers command from the Command Palette, select a server, and then choose an action from the list.

  

Automatically start MCP servers

When you add an MCP server or change its configuration, VS Code needs to (re)start the server to discover the tools it provides.

You can configure VS Code to automatically restart the MCP server when configuration changes are detected by using the

MCP server trust

MCP servers can run arbitrary code on your machine. Only add servers from trusted sources, and review the publisher and server configuration before starting it. Read the Security documentation for using AI in VS Code to understand the implications.

When you add an MCP server to your workspace or change its configuration, you need to confirm that you trust the server and its capabilities before starting it. VS Code shows a dialog to confirm that you trust the server when you start a server for the first time. Select the link to MCP server in the dialog to review the MCP server configuration in a separate window.

If you don't trust the server, it is not started, and chat requests continue without using the tools provided by the server.

You can reset trust for your MCP servers by running the MCP: Reset Trust command from the Command Palette.

Synchronize MCP servers across devices

With Settings Sync enabled, you can synchronize settings and configurations across devices, including MCP server configurations. This allows you to maintain a consistent development environment and access the same MCP servers on all your devices.

To enable MCP server synchronization with Settings Sync, run the Settings Sync: Configure command from the Command Palette, and ensure that MCP Servers is included in the list of synchronized configurations.

Troubleshoot and debug MCP servers

MCP output log

When VS Code encounters an issue with an MCP server, it shows an error indicator in the Chat view.

Select the error notification in the Chat view, and then select the Show Output option to view the server logs. Alternatively, run MCP: List Servers from the Command Palette, select the server, and then choose Show Output.

Debug an MCP server

You can enable development mode for MCP servers by adding a dev key to the MCP server configuration. This is an object with two properties:

• watch: A file glob pattern to watch for files change that will restart the MCP server.
• debug: Enables you to set up a debugger with the MCP server. Currently, VS Code supports debugging Node.js and Python MCP servers.

Learn more about MCP development mode in the MCP Dev Guide.

Centrally control MCP access

Organizations can centrally manage access to MCP servers via GitHub policies. Learn more about enterprise management of MCP servers.

Frequently asked questions

Can I control which MCP tools are used?

• Select the Tools button in the Chat view when using agents, and toggle specific tools on/off as needed.
• Add specific tools to your prompt by using the Add Context button or by typing #.
• For more advanced control, you can add rules to your .github/copilot-instructions.md file. For example, add a rule like "When querying the database, use the read-only MCP tool instead of direct SQL" or "Prefer the GitHub MCP server for repository operations" to guide tool selection.

The MCP server is not starting when using Docker

Verify that the command arguments are correct and that the container is not running in detached mode (-d option). You can also check the MCP server output for any error messages (see Troubleshooting).

I'm getting an error that says "Cannot have more than 128 tools per request."

A chat request can have a maximum of 128 tools enabled at a time due to model constraints. If you have more than 128 tools selected, reduce the number of tools by deselecting some tools or whole servers in the tools picker in the Chat view, or ensure that virtual tools are enabled (

Related resources

• Model Context Protocol Documentation
• Model Context Protocol Server repository
• Use agents in VS Code chat