Skip to main content
Glama
TestingBot MCP Server

TestingBot MCP Server

Official

runMaestroTest

Start a Maestro test run on a TestingBot device and get the run ID immediately; poll its status and fetch results after completion.

Instructions

Start a Maestro test run on a TestingBot device. Returns immediately with the run ID — it does NOT wait for completion. Poll with getMaestroRunStatus, then fetch getMaestroRunResults once completed.

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": {
      "projectId": "<projectId>",
      "platformName": "<platformName>"
    },
    "name": "runMaestroTest"
  }
}

Input Schema

NameRequiredDescriptionDefault
envNoEnvironment variables passed to the Maestro flows
nameNoA name for this test run, shown in the TestingBot dashboard
versionNoOS version (e.g. "14")
otherAppsNoUp to 4 companion app URLs (tb:// from uploadMaestroCompanionApp, or http(s)://) installed alongside the app under test
projectIdYesProject ID returned by uploadMaestroApp
deviceNameNoDevice name, supports wildcards/regex (e.g. "Pixel 8", "iPhone 1[4-6]", "*"). Default: any device
realDeviceNoRun on a physical device instead of an emulator/simulator (required for .ipa apps)
shardSplitNoSplit flows across this many parallel devices
excludeTagsNoSkip flows with these Maestro tags
includeTagsNoOnly run flows with these Maestro tags
platformNameYesMobile platform to run on
tunnelIdentifierNoIdentifier of a running TestingBot Tunnel (from startTunnel) for the app to reach localhost / private-network backends through. Without it the account's newest running tunnel, if any, is used. On Android, `localhost` / `127.0.0.1` never go through the tunnel: in flows and app config, use a hostname that resolves to 127.0.0.1 on the tunnel's machine instead, e.g. http://myapp.localtest.me:3000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.2/5.0
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 it discloses the single most consequential trait: the call is asynchronous and returns a run ID rather than blocking. It omits cost/duration implications, permission or project-scoping requirements, and what happens on device unavailability, leaving real gaps for a device-provisioning mutation.

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?

Three short sentences, all earning their place: action, non-blocking contract, and the exact follow-up sequence. The critical async caveat is front-loaded rather than buried.

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 12-parameter async launch tool with no output schema and no annotations, the description supplies the return contract (run ID) and the polling chain, which is what an agent most needs. Device-availability failure handling and prerequisite steps (uploadMaestroApp, uploadMaestroFlows) are left implicit.

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% and several parameters are documented in depth (tunnelIdentifier, otherApps, deviceName), so the structured field already does the heavy lifting. The description adds only the framing that projectId/device context comes from a prior upload step; it contributes little parameter meaning beyond 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 ('Start a Maestro test run on a TestingBot device') and immediately carves out scope: it does not wait for completion. An agent can distinguish this from retryMaestroRun or cancelMaestroRun without opening any schema.

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?

Gives explicit workflow routing: poll with getMaestroRunStatus, then fetch getMaestroRunResults once completed. It does not address when to prefer retryMaestroRun or the other test-run siblings, so it stops just short of full alternative coverage.

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