TesterArmy MCP Server
io.github.tester-army/testerarmy
AI agents that test your web and mobile apps like real users on every pull request.
What is the TesterArmy MCP server?
The TesterArmy MCP server integrates AI-powered QA testing into your development workflow. It allows agents to create, organize, and execute browser and mobile tests against your applications, then validate results through JSON output. TesterArmy runs as a hosted MCP server that authenticates via OAuth, eliminating the need for manual API key management.
TesterArmy provides cloud-based QA automation for web and mobile apps, enabling AI agents to run tests with plain-language steps, manage test environments, and deliver concrete validation feedback to coding agents. It integrates directly into CI/CD pipelines and works with Claude, Cursor, and other MCP-compatible tools.
How to install TesterArmy
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
projects list— List all projects and retrieve project IDs for test management.tests list— List saved tests for a specific project.tests run— Execute a saved test and optionally wait for results in JSON format.tests create— Create new saved tests with plain-language steps.groups list— List test groups within a project.groups run— Run an entire test group and retrieve results.environments— Save and select cloud-reachable preview or tunnel URLs as project environments.
Use cases
- Automatically run smoke tests and regression suites on every pull request to catch bugs before merge.
- Create plain-language test scenarios that AI agents can understand and execute against staging or preview environments.
- Validate UI changes and user workflows across browsers and mobile devices without manual QA effort.
- Feed test results back to coding agents to guide fixes and ensure quality gates are met.
- Organize and manage QA coverage across multiple projects and environments from a single dashboard.
TesterArmy MCP server FAQ
TesterArmy is a cloud-based QA platform that lets AI agents test web and mobile apps like real users. It executes browser and mobile checks against saved test scenarios and returns detailed results for validation.
The README does not specify pricing. Visit tester.army for current plans and free-tier availability.
Open Cursor's Customize menu and search for 'testerarmy', or add it manually to ~/.cursor/mcp.json with the URL https://tester.army/mcp.
Run 'claude mcp add --transport http testerarmy https://tester.army/mcp' or add it to your MCP configuration file.
No. The hosted MCP server at https://tester.army/mcp uses OAuth sign-in through your TesterArmy account. The CLI tool requires an API key from tester.army/dashboard/profile/api-keys.
The MCP server uses OAuth (no API key needed). The CLI requires an API key created in your TesterArmy dashboard.
README (reference)
Source of truth, from the repository.
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 through JSON output.
- Feed concrete validation back to coding agents.
Start here:
- Docs: tester.army/docs
- Platform: tester.army
- API keys: tester.army/dashboard/profile/api-keys
https://github.com/user-attachments/assets/f7524c3f-018e-46eb-9bae-cb69335fda64
</p>Quickstart
Install globally:
npm install -g testerarmy
Then create API key:
tester.army/dashboard/profile/api-keys
Authenticate (pick one):
ta auth
Or run without install:
npx testerarmy --help
Find a project and its saved tests, then wait for a cloud run:
ta projects list --json
ta tests list --project <projectId> --json
ta 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:
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.
Claude Code:
claude mcp add --transport http testerarmy https://tester.army/mcp
Codex:
codex mcp add testerarmy --url https://tester.army/mcp
Or add it to ~/.codex/config.toml and run codex mcp login testerarmy:
[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:
{
"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:
codex plugin marketplace add tester-army/cli
codex 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.mdexamples/tests/01-landing-page.mdexamples/tests/02-auth-smoke.mdexamples/tests/03-project-create.mdexamples/prompts/ad-hoc-regression.md
Run a saved smoke group:
ta groups list --project <projectId> --json
ta 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
Related MCP servers

io.github.tesults/tesults-mcp
Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.
Search 31,000+ open US grants, federal contracts, and foundations. Checked daily, free tier.
View repository →
io.github.teunlao/vidin
Turn a screen recording into agent-readable annotated keyframes. MCP server + CLI on ffmpeg.
21 paid data tools plus free quote/budget inspection, with bounded USDC payments on Base.
View repository →
textbee SMS
Send and read SMS through your own Android phone via textbee.dev, the open-source SMS gateway.

ViralQuery
Protected research briefs, bounded scrolls, and private video feeds for agents.

