<!-- VS Code and GitHub Copilot setup — Uptimely -->
> Markdown version of https://getuptimely.com/agent-setup/vscode — the page itself is the canonical copy.

AI agents

# Connect Uptimely to VS Code and GitHub Copilot

Onboard your AI agent to Uptimely+7

Configure

## Register the MCP server

Add this to `.vscode/mcp.json`, merging with any existing entry rather than replacing it:

```
{
  "servers": {
    "uptimely": {
      "type": "http",
      "url": "https://app.getuptimely.com/api/mcp"
    }
  }
}
```

Copy the config entry

Sign in

## Authorize the connection

VS Code shows a sign-in prompt the first time the server is started from the MCP view. The root key is `servers`, not `mcpServers`. Equivalent one-liner: `code --add-mcp '{"name":"uptimely","type":"http","url":"https://app.getuptimely.com/api/mcp"}'`.

Verify

## Confirm it worked

Ask VS Code and GitHub Copilot to call `search_tools`, then `execute_typescript` with `return await external_uptimely_project_list({});`. A client that lists `uptimely_project_list` as its own tool can call it directly. A JSON list of your projects — even an empty list — means the connection is live.

If you also configured the SDK or REST API, this should answer HTTP 200 with a JSON body whose `data` is a list of monitors:

```
curl -sS -H "Authorization: Bearer $UPTIMELY_API_KEY" https://app.getuptimely.com/v1/monitors
```

Copy the check

Reference

## More

Read on VS Code and GitHub Copilot's own docs (checked 2026-09-22): <https://code.visualstudio.com/docs/agent-customization/mcp-servers>

Or fetch the raw, machine-readable instructions this page is rendered from: [https://getuptimely.com/agent-setup/prompt.md](https://getuptimely.com/agent-setup/prompt.md)