🎩 You're Invited:Meet the Socket team at Black Hat in Las Vegas, August 3-6.RSVP
Sign In

@fasteningcode/claudetest

Package Overview
Dependencies
Maintainers
1
Versions
3
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@fasteningcode/claudetest

MCP server plugin for enterprise Playwright & Appium testing

latest
npmnpm
Version
0.0.3
Version published
Maintainers
1
Created
Source

@fasteningcode/claudetest

Enterprise-grade Playwright (web) and Appium (mobile) test automation for Claude.
Generate missing tests, diagnose CI failures, and open fix PRs — all from a single conversation.

npm version license

What it does

ClaudeTest is a Model Context Protocol (MCP) server that gives Claude direct access to your GitHub repositories and CI pipeline.

You → Claude → ClaudeTest MCP → GitHub API / GitHub Actions
                                ↓
                        Playwright / Appium test files
                                ↓
                        Pull request on your repo

Tools

ToolWhat it does
analyze_repoScans your repo and returns a prioritized list of untested flows
generate_testsWrites Playwright (web) or Appium (mobile) test files
run_testsTriggers a GitHub Actions workflow and waits for results
diagnose_failureReads CI logs and explains the root cause in plain English
create_prCommits generated tests to a new branch and opens a PR

Quickstart

Claude.ai (remote)

Find ClaudeTest in the Claude.ai integrations directory, click Connect, and authorize GitHub access.

Claude Code (local)

npx @fasteningcode/claudetest --stdio

Add to .claude/settings.json:

{
  "mcpServers": {
    "claudetest": {
      "command": "npx",
      "args": ["@fasteningcode/claudetest", "--stdio"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token"
      }
    }
  }
}

Self-hosted (Docker)

docker run -p 3000:3000 \
  -e GITHUB_TOKEN=ghp_your_token \
  ghcr.io/fasteningcode/claudetest:latest

Example conversations

Analyze a repo for coverage gaps

Analyze https://github.com/your-org/your-app for missing test coverage

Generate Playwright tests

Generate Playwright tests for the high-priority gaps you found

Generate Appium tests

Generate Appium tests for the untested screens in https://github.com/your-org/mobile-app

Diagnose a CI failure

Diagnose the failure in run 123456789 in https://github.com/your-org/your-app

Open a PR with generated tests

Open a PR with the generated tests on a branch called feat/claudetest

GitHub permissions required

ScopeReason
repo readRead source files and file tree
repo writeCreate branches and commit test files
workflow writeTrigger and read GitHub Actions runs
pull_requests writeOpen PRs with generated tests

Auth

Remote (Claude.ai): ClaudeTest uses OAuth — Claude.ai manages the GitHub token flow for you.

Local / self-hosted: Set GITHUB_TOKEN environment variable with a personal access token with repo and workflow scopes.

License

MIT

Keywords

claude

FAQs

Package last updated on 13 May 2026

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts