TesterArmy

io.github.tester-armyPublished by GitHub account tester-armyv1.0.0Updated Oct 25, 2026

Agents that test your web and mobile app like real users, on every pull request.

VerifiedStreamable HTTPWeb executableBrowser AutomationDeveloper Tools

Overview

AI-generated overview

Hosted MCP server for TesterArmy that lets an assistant create, run and inspect cloud QA tests for web and mobile apps.

What you can do
  • Create and organize saved tests written as plain-language steps
  • Run browser and mobile checks against saved project environments
  • Wait for cloud runs and inspect transcripts, recordings and JUnit reports
  • Schedule test groups, launch discovery runs and triage the issues found
  • Feed concrete validation results back to coding agents
When to use it
Useful when an agent should verify web or mobile app changes like a real user, for example running a saved smoke group on a pull request or validating a preview URL. It fits teams already using the TesterArmy dashboard for QA coverage.
Requirements
Remote Streamable HTTP endpoint at tester.army/mcp; no local install needed. Requires a TesterArmy account, signed in through OAuth (no API key to paste for MCP). The CLI alternative needs Node.js via npm and an API key. Runs execute in TesterArmy cloud, so a cloud-reachable preview or tunnel URL is needed to test local changes.
Before you install
Runs are queued and executed in TesterArmy's cloud, so test steps, target URLs and results are sent to a third party. Without waiting, a successful command only confirms the run was queued, not that it passed. Tests and environments are created and changed in your dashboard account, and the CLI path requires an API key that should be kept secret.

Installation

In SourceWeft

  1. Open TesterArmy in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.tester-army%2Ftesterarmy/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "testerarmy": {
      "type": "http",
      "url": "https://tester.army/mcp"
    }
  }
}

README

[TesterArmy CLI]

Quickstart | Docs | Platform | API Keys | Skills | MCP | Examples

[npm version] [npm downloads] [MIT license]

Agents that test your app like real users.

TesterArmy CLI (testerarmy / ta) manages QA coverage in the TesterArmy dashboard and queues runs that execute in TesterArmy cloud.

  • Create and organize saved tests with plain-language steps.
  • Run browser and mobile checks against saved environments.
  • Wait for results and inspect run transcripts, recordings, and JUnit reports.
  • Schedule groups, explore with discovery runs, and triage the issues they find.
  • Feed concrete validation back to coding agents.

Start here:

https://github.com/user-attachments/assets/f7524c3f-018e-46eb-9bae-cb69335fda64

Quickstart

Install globally:

bash
npm install -g testerarmy

Then create API key:

tester.army/dashboard/profile/api-keys

Authenticate (pick one):

bash
ta auth

Or run without install:

bash
npx testerarmy --help

Find a project and its saved tests, then wait for a cloud run:

bash
ta projects list --jsonta tests list --project <projectId> --jsonta tests run <testId> --wait --json

Use IDs returned by the list commands. Without --wait, a successful command only confirms that the run was queued. To validate development changes, save a cloud-reachable preview or tunnel URL as a project environment and select it with --env <nameOrSlug>.

Skill Installation

Use skills CLI install:

bash
npx skills add tester-army/cli

MCP server and plugins

TesterArmy also runs as a hosted MCP server at https://tester.army/mcp (Streamable HTTP). It signs you in with your TesterArmy account through OAuth, so there is no API key to create or paste. MCP and the CLI cover the same features; pick whichever your agent drives more easily.

Claude Code:

bash
claude mcp add --transport http testerarmy https://tester.army/mcp

Codex:

bash
codex mcp add testerarmy --url https://tester.army/mcp

Or add it to ~/.codex/config.toml and run codex mcp login testerarmy:

toml
[mcp_servers.testerarmy]url = "https://tester.army/mcp"

Cursor: open Customize and search for testerarmy, or click Add to Cursor on the marketplace listing. If the plugin is not listed yet, add the server by hand to ~/.cursor/mcp.json:

json
{  "mcpServers": {    "testerarmy": {      "url": "https://tester.army/mcp"    }  }}

This repo is also a plugin that installs the MCP server and the testerarmy-cli skill together.

Claude Code: run /plugin marketplace add tester-army/cli, then /plugin install testerarmy@testerarmy-agent-skills.

Codex: the repo is a plugin marketplace too, so until TesterArmy appears in the Plugins Directory you can add it from here:

bash
codex plugin marketplace add tester-army/clicodex plugin add testerarmy@testerarmy-agent-skills

The plugin registers the hosted server for you; sign in once with codex mcp login testerarmy, or accept the sign-in prompt the ChatGPT app shows at install. In the ChatGPT desktop app, open this repository in Codex and the marketplace appears as a source in the Plugins tab.

Full reference for the server and its tools: https://docs.tester.army/cli/mcp

Examples

Use the markdown scenarios in examples/ as authoring references when creating saved dashboard tests with ta tests create.

  • examples/TESTER.md
  • examples/tests/01-landing-page.md
  • examples/tests/02-auth-smoke.md
  • examples/tests/03-project-create.md
  • examples/prompts/ad-hoc-regression.md

Run a saved smoke group:

bash
ta groups list --project <projectId> --jsonta tests run --group <groupId> --project <projectId> --wait --json

Contributing

PRs welcome, especially for:

  • improving skill quality and references
  • better issue templates and triage process
  • better real-world test examples

License

MIT

Source: README.md at commit 0d63136

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 21, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts