Skip to main content
Glama

start_browser

Launch a real cloud browser and return its CDP URL so you can drive it with Playwright or Puppeteer across multiple tool calls. Stop it when done to end billing.

Instructions

Start a real cloud browser and return its CDP URL, so you can drive it yourself with Playwright or Puppeteer (connect_over_cdp) instead of handing the work to run_task. Use this when you want to write the browser steps, or need the page open across several of your own tool calls. Billed per browser; always call stop_browser when you are done. Without a proxy the browser uses Browsa's data-center IP.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_browser"
  }
}

Input Schema

NameRequiredDescriptionDefault
ttlNoHow long to keep it, e.g. "5m" or "1h". Default 10m.
proxyNoOne of two forms. Your own proxy: give host and port, or server as "host:port" / "socks5://host:port", plus username and password when it needs them. Or a tier of Browsa's built-in proxy network, billed per GB from credits: {"network": "datacenter"} or {"network": "residential", "country": "us"}, with nothing else next to network. The built-in network works only when the proxy_network tool reports enabled: call it first for the tiers, their countries and the price per GB.
countryNoISO-2 country, e.g. "us". Takes effect only with a proxy.
os_typeNoOperating system the browser presents, e.g. "macos", "windows".
profile_idNoReuse a saved identity (see list_identities) so the browser starts with its cookies and logins.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose the two costliest risks: "Billed per browser" and the requirement to call stop_browser. It also explains the default egress behaviour ("Without a proxy the browser uses Browsa's data-center IP"). What it does not cover is what happens at TTL expiry, whether the browser is auto-stopped, or whether the CDP URL is a secret credential, which keeps it below a 5.

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?

Four sentences, front-loaded with the capability and return value before the routing advice and the cost warning. Every sentence carries a distinct, actionable fact and there is no filler.

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?

With no output schema, the description compensates by naming the returned CDP URL, and it covers billing, cleanup, and the proxy-less default for a five-parameter launch tool with a nested proxy object. Gaps remain around TTL expiry behaviour, concurrency or rate limits, and whether the returned URL must be treated as a secret.

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

Parameters3/5

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

Schema description coverage is 100%, including a detailed nested proxy description that explains both proxy forms and the proxy_network prerequisite, so the schema already does the parameter work. The description adds only the proxy/egress default and implies the TTL via the stop_browser warning; it says nothing specific about ttl, os_type, country, or profile_id. Baseline 3 is appropriate.

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?

States a specific verb and resource ("Start a real cloud browser") and, unusually, the return value ("return its CDP URL"), plus the mechanism (connect_over_cdp with Playwright/Puppeteer). It explicitly distinguishes itself from the sibling run_task, so an agent can pick between them without opening a schema.

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?

Gives a positive selection rule ("Use this when you want to write the browser steps, or need the page open across several of your own tool calls") and names the alternative it replaces (run_task). It also states the mandatory follow-up, "always call stop_browser when you are done", which is the key lifecycle constraint.

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