Skip to main content
Glama

start_instance

Launch an Ubuntu desktop sandbox to browse the web or execute code, then access the stream URL to monitor the instance in real time.

Instructions

Start a Scrapybara Ubuntu instance. Use it as a desktop sandbox to access the web or run code. Always present the stream URL to the user afterwards so they can watch the instance in real time.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Handler for the 'start_instance' tool. Starts a new Scrapybara Ubuntu instance, initializes the browser, optionally authenticates using AUTH_STATE_ID, retrieves the stream URL, and returns the instance details including the stream URL.
    case "start_instance": { const instance = await client.startUbuntu(); await instance.browser.start({ abortSignal: currentController.signal, }); if (process.env.AUTH_STATE_ID) { await instance.browser.authenticate( { authStateId: process.env.AUTH_STATE_ID, }, { abortSignal: currentController.signal } ); } const streamUrlResponse = await instance.getStreamUrl({ abortSignal: currentController.signal, }); const streamUrl = streamUrlResponse.streamUrl; return { content: [ { type: "text", text: JSON.stringify({ ...instance, streamUrl }, null, 2), } as TextContent, ], }; }
  • Zod schema definition for the 'start_instance' tool input parameters (no parameters required).
    export const StartInstanceSchema = z.object({});
  • src/index.ts:72-77 (registration)
    Registration of the 'start_instance' tool in the ListToolsRequestHandler, including name, description, and input schema.
    { name: "start_instance", description: "Start a Scrapybara Ubuntu instance. Use it as a desktop sandbox to access the web or run code. Always present the stream URL to the user afterwards so they can watch the instance in real time.", inputSchema: zodToJsonSchema(StartInstanceSchema), },

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Scrapybara/scrapybara-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server