TesterArmy CLI MCP
TesterArmy CLI and MCP run end-to-end browser and mobile tests in the cloud from plain-language steps.
- 75 ★ on the repository
- Last commit
Extended access
Why this level
- Tests run in the TesterArmy cloud against externally reachable environments.
- Run transcripts and recordings are kept in the service dashboard.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/testerarmy-cliDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Tests run in the TesterArmy cloud against externally reachable environments.
- Run transcripts and recordings are kept in the service dashboard.
This is third-party code. Review the repository files before installing.
What it does
TesterArmy runs quality checks from the service dashboard and queues runs in its cloud. Tests are described as plain-language steps, run on saved environments in a browser and on mobile, awaited and inspected through transcripts, recordings and JUnit reports. Groups run on a schedule, discovery runs look for problems and found issues are triaged. There are two ways to drive it with the same features: the `testerarmy` CLI (command `ta`) or the hosted MCP server `https://tester.army/mcp`, with OAuth sign-in and no API key. The repository is also a plugin that installs the MCP server and the `testerarmy-cli` skill together for Claude Code, Codex and Cursor. To test local changes, save a preview or tunnel URL reachable from the cloud in the project.
Who it is for. Developers and QA engineers who want an agent to test a finished feature like a user and feed results back to code.
Good fit when
- After an edit the agent runs a saved test and waits for the result with a transcript.
- A test is written as plain-language steps and saved in the project.
- A nightly run of a test group is needed on a schedule.
- A discovery run hunts for problems on a new screen and the issues are triaged in the dashboard.
- Changes are checked on a cloud preview or tunnel.
Not a fit when
- You need a local run without a cloud: runs execute in the TesterArmy cloud.
- The tested app is not reachable from the internet and there is no tunnel.
- Tests must live as code in the repository: they are stored in the service dashboard.
Example request
Run the saved checkout test on our preview, wait for the result and tell me which step failed.MCP
- Transport
- http
- Authentication
- OAuth
Limitations
A TesterArmy account is required, and the CLI also needs an API key from the dashboard. Runs execute in the service cloud, so the environment under test must be reachable from outside (preview or tunnel) and saved as a project environment, selected with the `--env` flag. Without `--wait` the run command only confirms the run was queued. See `tester.army` for terms and plans. The repository was renamed and the old address redirects.
How to disable. Remove the plugin or MCP entry from the client (`claude mcp remove testerarmy`), run `npm uninstall -g testerarmy` and revoke API keys in the TesterArmy dashboard.
FAQ
How do I connect MCP?
In Claude Code: `claude mcp add --transport http testerarmy https://tester.army/mcp`. In Codex: `codex mcp add testerarmy --url https://tester.army/mcp`, then `codex mcp login testerarmy`.
How do I run a test through the CLI?
Find the ids with `ta projects list --json` and `ta tests list --project <projectId> --json`, then `ta tests run <testId> --wait --json`.
What does `--wait` do?
Without it the command only queues the run. With `--wait` the CLI waits for the result and returns it.
Is an API key needed for MCP?
No. The MCP server signs in through your TesterArmy account over OAuth, so no key is needed. For the CLI the key is created in the dashboard.
How do I install the skill and MCP together?
As a plugin: in Claude Code run `/plugin marketplace add tester-army/cli`, then `/plugin install testerarmy@testerarmy-agent-skills`. The plugin registers the hosted server and the `testerarmy-cli` skill.
Discussion
No questions or reviews yet.
Related
MCP serversMCP server, agent and skills for end-to-end UI tests where the agent drives the computer through vision on cloud machines
kogiQA MCP gives an agent a browser that finds page elements without selectors, for debugging web apps and writing e2e tests
A CLI from TestMu AI that writes end-to-end tests from requirements and runs them in a browser or on mobile, with a skill for your agent
An MCP server that spins up several browser agents to test a site for broken links, UI bugs and accessibility issues
MCP server: an agent sends GET, POST, PUT, DELETE and PATCH to your REST API and gets back status, headers and body
BrowserStack MCP Server: testing on real devices
BrowserStack MCP Server
The official BrowserStack MCP server: real devices, automated tests and test cases driven by an agent from your editor
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| TesterArmy CLI (this card) | yes | OAuth | 75 | |
| Playwright MCP | yes | not required | 39,570 | drives a browser on your machine on agent commands; TesterArmy runs saved tests in the cloud and keeps run recordings |
| QA Wolf CLI | no | 3,459 | also runs end-to-end tests through a CLI; here tests are plain-language steps connected through MCP |
README in short
The repository of the TesterArmy CLI and plugin: `ta` commands, MCP manifests for Claude Code, Codex and Cursor, the `testerarmy-cli` skill and a report template. The cloud service is run separately, and the MCP reference is at `docs.tester.army`.