Skip to main content
Glama
Sign In
Cat Burglar

Cat Burglar

by DrMkdaddy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Open browser

open

Launch an agent-controlled browser using stealth Chromium, full Chromium, or lightweight Rust, and reuse sessions to keep cookies and tabs; restart to apply new options.

Instructions

Launch the agent browser. Default engine is patchright (stealth Chromium). Use engine=chromium for full-fidelity devtools/perf/local testing, or engine=obscura for a lightweight Rust engine (lower memory, strongest tracker blocking). Reusing an open browser keeps cookies and tabs; pass restart=true to relaunch with new options.

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": "open"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoOptional URL to open after launch.
proxyNoHTTP or SOCKS5 proxy URL.
engineNo
localeNo
profileNoObservation/verbosity profile (model-adaptive).
restartNoClose an open browser first.
stealthNoObscura only: enable stealth mode (default true).
headlessNo
humanizeNoHumanized mouse/typing (default true).
timezoneNo
viewportNo
user_agentNo
allow_privateNoAllow localhost/LAN/private IPs. Defaults to the server config.
block_trackersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, so the description must carry the behavioral burden, and it does: it explains that repeated calls reuse the existing browser and preserve cookies and tabs, and that restart=true relaunches with new options. It also states engine-specific traits (stealth defaults, memory). It does not describe failure modes or permissions.

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 tight sentences with the core action first, then engine options, then reuse/restart semantics. Every clause carries decision-relevant information and nothing is repeated.

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

Completeness5/5

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

For a launch tool with no output schema and all-optional parameters, the description covers the decisions an agent must make: which engine, whether to reuse or restart, and what the defaults are. Remaining undocumented parameters have sensible defaults and do not block a correct call.

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?

With 14 parameters and only 50% schema description coverage, the description adds real meaning for the engine enum's three modes and the restart flag's relaunch behavior. It adds nothing for proxy, profile, locale, timezone, viewport, user_agent, headless, block_trackers, or allow_private beyond what the schema already says. That is adequate but far from complete for a 14-parameter tool.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Launch the agent browser.' It immediately distinguishes launch semantics from a navigation or session tool by explaining default engine and reuse behavior. It does not explicitly name a sibling, so it stops short of a full 5.

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

Usage Guidelines4/5

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

It gives concrete selection guidance: use the default patchright, choose chromium for devtools/perf/local testing, or obscura for low memory and tracker blocking. It also explains the reuse-vs-restart condition. It lacks explicit when-not-to-use guidance or a pointer to the close/status siblings.

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

Deploy Server

Other Tools