Skip to main content
Glama
TestingBot MCP Server

TestingBot MCP Server

Official

startTunnel

Starts a TestingBot Tunnel so remote browsers and devices can reach localhost, private-network, or intranet URLs; call before local or private tests and pass the returned identifier to test runs.

Instructions

Start a TestingBot Tunnel on this machine so remote browsers and devices can reach localhost, private-network and intranet URLs. Call this BEFORE testing any local or private URL. Waits until the tunnel is ready (can take up to a minute on first use, which downloads the tunnel) and returns its identifier — pass that as tunnelIdentifier to tb_openBrowser / runMaestroTest. Requires Java 17+ on this machine. The tunnel keeps running until stopTunnel is called or the MCP server exits.

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": "startTunnel"
  }
}

Input Schema

NameRequiredDescriptionDefault
noBumpNoDo not re-sign HTTPS traffic in the tunnel. Use when the site uses certificate pinning or client certificates.
sharedNoShare the tunnel with the other members of the TestingBot team
noCacheNoDisable the tunnel's caching of static assets
tunnelIdentifierNoIdentifier for the tunnel. Optional — a unique one is generated. Starting again with an identifier this server already runs returns the running tunnel.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses blocking behavior and latency ('waits until the tunnel is ready... up to a minute on first use'), a side effect (downloading the tunnel), an environment prerequisite (Java 17+), and lifecycle semantics (runs until stopTunnel or MCP server exit). The idempotency note on reusing an identifier is also surfaced.

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?

Front-loaded with the action and the prerequisite ordering rule, then the latency caveat, return value, requirement, and lifecycle. Every sentence adds a distinct operational fact with no redundancy.

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 no output schema, the description correctly explains the return value and its intended use, and covers prerequisites and lifecycle. The only shortfall is that it does not say what a failure looks like (e.g. missing Java or unreachable tunnel), which would matter for an agent deciding whether to retry.

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?

Schema coverage is 100%, so the baseline is 3; the description earns extra by tying the optional tunnelIdentifier to its downstream use and by implying a generated value is returned when omitted. The three boolean flags are left entirely to the schema, which is acceptable given full coverage.

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 TestingBot Tunnel on this machine') plus the concrete effect ('so remote browsers and devices can reach localhost, private-network and intranet URLs'). This clearly separates it from stopTunnel and from the browsing siblings it feeds.

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 an explicit ordering rule ('Call this BEFORE testing any local or private URL') and names the downstream consumers of the returned identifier (tb_openBrowser / runMaestroTest). It also states the lifecycle boundary against stopTunnel, so the agent knows when the tunnel is no longer needed.

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