Give GitHub Copilot in VS Code access to skill discovery through one MCP connection. Describe your task, and your agent can find and load relevant instructions without installing each skill separately.

Before you start

Use current VS Code with GitHub Copilot Chat and permission to use MCP servers in your workspace.

You need a 9octopus account to approve access. You can sign in or create one during connection. Use the account for this environment; staging and production accounts are separate.

1. Add 9octopus to GitHub Copilot in VS Code

Use this server URL with remote MCP over Streamable HTTP and OAuth:

https://app.9octopus.work/mcp
  1. Add a remote HTTP server. Open the Command Palette and run MCP: Add Server. Select HTTP, paste the server URL above, name it 9octopus, and choose a configuration location.
  2. Alternatively, configure the workspace file. Merge this entry into .vscode/mcp.json if you prefer editing configuration. The VS Code format uses servers as the top-level key.
    {
  "servers": {
    "9octopus": {
      "type": "http",
      "url": "https://app.9octopus.work/mcp"
    }
  }
}

The examples name the connection 9octopus. If you choose another name, use that name in commands and prompts. If you already have a connection, inspect it before adding another.

2. Sign in and approve access

Run MCP: List Servers, select 9octopus, and start it. Review any trust prompt and complete OAuth sign-in when requested.

On the 9octopus consent page, check the client name, sign in, and approve access. Keep the agent open until it finishes connecting. You do not need to paste a bearer token into your configuration.

3. Check the connection and try a task

Open Copilot Chat in Agent mode and make sure the 9octopus tools are enabled in the tool picker.

You can also open Connected agents in 9octopus to confirm that the connection is active. Then send this prompt to GitHub Copilot in VS Code:

Use the 9octopus MCP connection to find public skills for reviewing a landing page’s accessibility. Show me the relevant descriptions and sources. Load the best fit, confirm its exact version, and explain what access you need before starting the review.

Your agent should discover skills, load the selected release, and read its instructions. It still needs the tools and permissions required to perform the task. If no suitable skill exists, refine the task or browse public skills.

Public task recommendations may send your task description to OpenAI. Keep secrets and private repository contents out of discovery prompts.

Optional: help your agent discover skills as you work

Open Connections and select Agent instructions. Copy the guidance into your client’s persistent instructions, or merge the downloaded AGENTS.md into a supported instruction file. Keep existing rules; supported filenames and settings vary by agent.

Troubleshooting

  • Use MCP: List Servers to inspect output or restart the connection. If the tool list is stale, run MCP: Reset Cached Tools. Check workspace policy if MCP is disabled.
  • Expired consent or HTTP 401: restart authentication from the agent and complete the new browser flow. An old consent URL cannot be reused.
  • Pending in Connected agents: the agent has not finished the token exchange. Retry sign-in, then revoke any abandoned pending entry.
  • Need to disconnect? Revoke this connection in Connected agents. To reconnect later, clear its saved authentication in the client and sign in again.

Setup reference: GitHub Copilot in VS Code MCP documentation. Instructions reviewed October 27, 2026; client menus and plan availability can change.

Using a different agent? Choose another setup guide or follow the general MCP connection instructions.