Skip to main content
Glama
TestingBot MCP Server

TestingBot MCP Server

Official

tb_login

Authenticate with TestingBot via browser authorization to save credentials for later tool calls; use the device-code flow when the browser cannot reach your machine.

Instructions

Authenticate with TestingBot — no API key or secret to copy or paste. By default it opens your browser, you click Authorize, and the credentials are captured automatically and saved to ~/.testingbot/credentials (used by every later tool call this session — no restart). If your browser can't reach this machine (SSH / remote / dev container / web), it falls back to a short URL + code you enter in any browser; pass mode:"device" to force that. After authorizing in the browser, call tb_login again to finish. Call this whenever credentials are missing.

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": "tb_login"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoHow to authenticate. "auto" (default): open the browser and capture the callback on a local port; falls back to a copy-paste code on headless/remote machines. "loopback": force the browser flow. "device": force the copy-paste code flow (use this on SSH/remote/dev-container/web setups where the browser can't reach this machine).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that a browser window opens, that the callback is captured on a local port, that credentials persist to disk and apply to every later call in the session without a restart, and that headless environments fall back to a code flow. It stops short of stating credential lifetime/expiry, whether an existing credentials file is overwritten, or what a failed authorization looks like.

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?

Front-loaded with the core action and credential location, then the fallback, then the completion step. Slightly redundant: the device/copy-paste fallback is explained once in prose and again in the mode enum, and 'no API key or secret to copy or paste' is a marketing line rather than operational guidance.

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 a single optional parameter with no output schema, the description covers the two-phase flow, environment-dependent fallback, and credential persistence. The only gap is what the call returns on success versus failure, which matters because the agent must decide whether to retry or call again.

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 mode enum already documents 'auto', 'loopback', and 'device' in detail. The description restates the default and the device-forcing hint, which reinforces but does not meaningfully extend the schema.

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 ('Authenticate with TestingBot') plus the concrete effect: credentials captured automatically and saved to ~/.testingbot/credentials. It is immediately distinguishable from the tb_* browser-automation siblings, which all operate on an already-authenticated session.

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?

Explicitly says when to call it ('whenever credentials are missing'), which mode is default, when the device flow is forced (SSH/remote/dev container/web), and that a second tb_login call is required to finish after browser authorization. That covers the full invocation lifecycle with no inference needed.

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