Skip to main content
Glama
TestingBot MCP Server

TestingBot MCP Server

Official

startLiveSession

Start an interactive TestingBot live testing session for desktop or mobile, returning a dashboard link to open and confirm. Use a tunnel ID for localhost or private-network URLs.

Instructions

Start an interactive live testing session on TestingBot. Returns a link that opens the session in the user's TestingBot dashboard (they confirm with Start). Supports desktop browsers (Chrome, Firefox, Safari, Edge, IE) and mobile emulators/simulators (Android, iOS). For localhost / private-network URLs, start a tunnel first (startTunnel) and pass its numeric ID as tunnelId.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "platformType": "<platformType>",
      "desiredURL": "<desiredURL>",
      "desiredOS": "<desiredOS>",
      "desiredOSVersion": "<desiredOSVersion>"
    },
    "name": "startLiveSession"
  }
}

Input Schema

NameRequiredDescriptionDefault
tunnelIdNoNumeric ID of a running TestingBot Tunnel (from startTunnel or getTunnelList) to route the session through. Needed for localhost / private-network URLs.
desiredOSYesOperating system: 'Windows', 'Mac', 'Linux' for desktop; 'android', 'ios' for mobile
desiredURLYesThe URL to open in the browser
platformTypeYesPlatform type: 'desktop' for desktop browsers or 'mobile' for mobile devices
desiredDeviceNoDevice name for mobile (e.g., 'iPhone 14', 'Galaxy S23')
desiredBrowserNoBrowser name for desktop: 'chrome', 'firefox', 'safari', 'edge', 'ie'
desiredOSVersionYesOS version (e.g., '11' for Windows 11, '16.0' for iOS 16)
desiredBrowserVersionNoBrowser version or 'latest' (default: latest)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the non-obvious outcome — a returned link that opens the dashboard where the user must confirm with Start — but says nothing about authentication requirements, session lifetime or billing/credit consequences, or what happens if the tunnelId is invalid or missing.

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

Conciseness4/5

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

Three front-loaded sentences: purpose, then return/confirmation behavior, then the tunnel prerequisite. It is efficient overall, though the enumeration of supported browsers and OSes partially duplicates the schema's enums and could be trimmed.

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?

For an 8-parameter creation tool with no output schema, the description covers the essential flow: what is created, what is returned, how the user completes it, and the key prerequisite. Auth/permission expectations and failure behavior are the remaining gaps, but the core call pattern is complete.

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 coverage is 100% and the schema already documents every parameter, including tunnelId's provenance ('from startTunnel or getTunnelList') and its localhost use case. The description largely restates that tunnel guidance and lists browser/platform support that mirrors the enum values, so it adds little meaning beyond the schema.

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 ('Start an interactive live testing session on TestingBot') and states that it covers both desktop browsers and mobile emulators, which distinguishes it from narrower siblings. It never explicitly contrasts itself with startDesktopLiveSession or startMobileLiveSession, so the agent must infer that this is the general-purpose entry point.

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

Usage Guidelines3/5

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

Usage context is given only for the tunnel case: localhost/private-network URLs require calling startTunnel first and passing its numeric ID. No guidance is offered on when to choose this tool over the sibling startDesktopLiveSession / startMobileLiveSession tools, even though their names suggest overlapping scope.

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