Log inSubmit server
Wopee MCP logo

Wopee MCP

by Wopee-io

Connects MCP-compatible agents to Wopee.io for browser-based analysis, test generation, execution, reporting, and artifact management.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Wopee MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "wopee-io-wopee-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "wopee-mcp"
      ],
      "env": {
        "WOPEE_PROJECT_UUID": "YOUR_VALUE_HERE",
        "WOPEE_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

Wopee-io/wopee-mcp connects MCP-compatible agents to Wopee.io projects for autonomous web application testing. It can crawl an application in a real browser, generate app context, user stories, test cases, reusable test assets, and Playwright code, then dispatch tests and retrieve reports. Project and suite tools also manage runtime variables, chat updates, and GitHub issues. Reach for it when an agent needs to analyze a web app or coordinate asynchronous end-to-end test runs through Wopee.io.

Use cases

  • Crawl a web app and map its pages
  • Generate user stories and test cases from app context
  • Dispatch autonomous browser tests and review verdicts
  • Retrieve Playwright code for selected test cases
  • Create GitHub issues from discovered failures

Key features

  • Real-browser application crawling
  • AI-generated testing artifacts
  • Asynchronous autonomous test execution
  • Suite and test inventory management
  • Playwright code retrieval
  • Project variables, chat, and GitHub issue tools

Tools15

What Wopee MCP lets your agent do. Expand a tool for its parameters.

Verified live~4.6k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

19/20 checks healthy over the last 85d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 16d ago via OSV.dev · wopee-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars4Stargazers on the source repository.
npm downloads1.3kPackage downloads in the last 30 days.
Last commitTodayMost recent push to the default branch.
Tools exposed15Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Wopee MCP works

What Wopee-io/wopee-mcp does

Wopee-io/wopee-mcp exposes Wopee.io testing workflows through MCP. An agent can discover existing analysis suites, create a blank suite for manual setup, or start a new crawl from an application URL. The crawl uses a real browser to inspect pages and map the application structure.

Once a suite exists, the agent can generate application context, general user stories, user stories with test cases, test case steps, reusable test cases, and reusable test case steps. Playwright code can be retrieved for individual test cases. Caller-supplied artifacts can also be uploaded or replaced, which supports bringing context from systems such as JIRA or Confluence into a suite.

The server also exposes project-level operations. Agents can read or update runtime variables, post and read project chat messages, and create GitHub issues in the repository connected to the Wopee.io project.

How it works

Most suite operations use a suiteUuid. Fetch existing suites first, or create one with wopee_create_blank_suite or wopee_dispatch_analysis. The analysis dispatch creates a suite and launches an asynchronous browser crawl; it can receive a starting URL, login credentials, cookie preferences, variables, and additional instructions.

Artifact generation follows an order: application context should come before user stories, and user stories should come before test cases. Generated content is retrieved separately with wopee_fetch_artifact. Existing content can be read and fully replaced with wopee_update_artifact.

Test execution is also asynchronous. wopee_dispatch_agent returns dispatch and tracking information rather than a final verdict. Use recent execution results or suite-specific executed test cases later to inspect progress and reports. For complete inventories, including authored tests that have never run, use wopee_fetch_test_inventory.

Setup and configuration

Run the server with Node.js using:

Terminal
npx wopee-mcp

Configure it as a stdio MCP server in an MCP-compatible client. The required environment variables are WOPEE_PROJECT_UUID, identifying the Wopee.io project, and WOPEE_API_KEY, providing API authentication. WOPEE_API_URL can point to an alternate endpoint for testing or development.

HTTPS proxy variables are supported for restricted networks, including HTTPS_PROXY and HTTP_PROXY. If an internal certificate or TLS-inspecting proxy is used, Node.js may need a trusted CA configured through NODE_EXTRA_CA_CERTS. Disabling TLS verification with NODE_TLS_REJECT_UNAUTHORIZED=0 is described only as a local debugging workaround.

Tools and capabilities

  • Discover, create, and rerun analysis suites.
  • Crawl applications with an autonomous browser agent.
  • Generate, fetch, and replace testing artifacts.
  • Dispatch asynchronous test execution and inspect reports.
  • View full test inventories with latest statuses and not-run cases.
  • Manage project and analysis runtime variables.
  • Exchange project chat messages and create connected GitHub issues.

Limitations and notes

Analysis dispatch creates a new suite and has a ten-second per-project dispatch interval; concurrent calls retry with exponential backoff. Agent execution generally takes one to three minutes, so dispatch confirmation is not a pass or fail result.

Artifact generation order affects output quality, and generating an existing artifact type overwrites its previous version. Updating an artifact replaces the full content rather than applying a patch. Playwright artifact retrieval requires a test case identifier such as US004:TC006.

A project must have its GitHub integration configured before issue creation works. Runtime variable keys must use uppercase characters and underscores; invalid keys are removed during server-side sanitization.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Wopee MCP

Wopee-io/wopee-mcp is an MCP server that connects AI agents to Wopee.io projects for browser-based web testing. Its main tools create and analyze suites, generate user stories and test cases, dispatch autonomous browser executions, retrieve reports and Playwright code, manage variables, and create GitHub issues.

Install it by configuring `npx wopee-mcp` as a stdio MCP server in your client. Set `WOPEE_PROJECT_UUID` and `WOPEE_API_KEY` in the server environment. Node.js 18 or newer is recommended.

Yes, Wopee-io/wopee-mcp works with Cursor because Cursor supports MCP and is named as a supported setup environment. Configure the server command and required Wopee.io environment variables in Cursor's MCP configuration.

Check results after dispatch with `wopee_fetch_recent_executions` or `wopee_fetch_executed_test_cases`. Test runs are asynchronous and may take one to three minutes. Use `wopee_fetch_test_inventory` when you need every authored test, including cases that have not run.

Generate the required test artifacts for a suite, then retrieve the `PLAYWRIGHT_CODE` artifact with `wopee_fetch_artifact`. The retrieval call must include a test case identifier such as `US004:TC006`.

Related MCP servers

All in Browser Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewWopee MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/wopee-io-wopee-mcp?style=directory)](https://allmcps.com/mcp/wopee-io-wopee-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/wopee-io-wopee-mcp"><img src="https://allmcps.com/api/badge/wopee-io-wopee-mcp?style=directory" alt="Wopee MCP on AllMCPs" /></a>