1. Conduid
  2. Browser
  3. server
MCP server · Browser

server

AI-assisted website testing with Playwright and Gherkin

Unclaimed MIT last commit 6 months ago playwrightdevtoolscucumberaigherkintesting
62Good

Scored 3 months ago · breakdown

About server

server is an MCP server published by letsrunit-hq in the Browser category: aI-assisted website testing with Playwright and Gherkin. It has been installed 0 times through Conduid.

Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx @letsrunit/mcp-server
Claude Code
claude mcp add letsrunit -- npx -y @letsrunit/mcp-server
npx
npx -y @letsrunit/mcp-server

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about server

Powered by Claude · Grounded in docs

I know everything about server. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

letsrunit

letsrunit is a browser testing tool that describes what your app should do in plain language rather than code. Tests are written in Gherkin, run by Cucumber.js, and integrate into any CI pipeline as standard files. You can write them by hand, generate them from a live URL, or let your AI coding agent produce them as part of its normal workflow.

Getting Started

Run the init tool inside your project:

npx letsrunit init

This will:

  • Install @letsrunit/cli as a local devDependency
  • Install @letsrunit/bdd and create cucumber.js if @cucumber/cucumber is detected
  • Create a features/ directory with an example feature file

Safe to re-run — all steps are idempotent.

CLI

The CLI is installed locally by letsrunit init. Run it via npx letsrunit or yarn letsrunit.

Command Description
letsrunit explore <url> Open a browser, let the AI explore the site, and optionally save a .feature file
letsrunit generate <url> Generate a Gherkin feature from instructions provided on stdin
letsrunit run <url> <feature> Execute a .feature file against the given URL

Options (all commands): -v / --verbose, -s / --silent, -o / --save <path>

MCP Server

The MCP server lets AI coding agents (Claude Code, Cursor, Codex, etc.) launch browsers, run Gherkin steps, take screenshots, and inspect pages directly inside your editor.

Install

Claude Code — add the marketplace once, then install the plugin to get both the MCP server and skill:

/plugin marketplace add letsrunit-hq/agent
/plugin install letsrunit@letsrunit

Other agents — add to your MCP config manually:

{
  "mcpServers": {
    "letsrunit": {
      "command": "npx",
      "args": ["-y", "@letsrunit/mcp-server"]
    }
  }
}

Agent Skill

The letsrunit skill gives your agent built-in knowledge of the Gherkin step library, locator syntax, and test-writing workflow. Requires the MCP server to be configured first.

The skill is included automatically when using the Claude Code plugin above. For other agents run

npx skills add letsrunit-hq/agent

Development

Read the development guide.

README mirrored from the source repository 3 months ago. The original is authoritative.

Questions

About server

How do I install server?

Run npx @letsrunit/mcp-server, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is server safe to use with an AI agent?

Its trust score is 62 out of 100 (good). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is server still maintained?

The last commit was 6 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.