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),
    },
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: the tool creates a desktop sandbox for web access or code execution, and it generates a stream URL for real-time viewing. However, it lacks details on permissions, rate limits, or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action, followed by usage context and a critical post-action step. Every sentence adds essential information with zero waste, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (starting an instance with streaming) and lack of annotations or output schema, the description is mostly complete. It covers purpose, usage, and output behavior, but could benefit from details on instance specifications or error cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description adds value by explaining the tool's purpose and output behavior, justifying a baseline score above the minimum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Start') and resource ('a Scrapybara Ubuntu instance'), and distinguishes it from siblings like 'stop_instance' and 'get_instances' by focusing on initiation rather than termination or querying.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use this tool ('Use it as a desktop sandbox to access the web or run code') and provides a clear post-action directive ('Always present the stream URL to the user afterwards'), offering strong guidance without mentioning alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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