# Endform

Endform lets an agent inspect Playwright runs and investigate failing or erratic tests. Use it to track down checks that break in CI.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 3 repo stars
- Author: endformdev
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/endformdev/skills
- Updated: 2026-10-28
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/endform

## What it does

The MCP server gives an agent access to test runs on Endform, where it can inspect failures and identify slow or inconsistent tests. It can also help repair a test, set it aside, or investigate its steps during a live run.

Run the server with `npx -y endform`. You can connect it directly or use a plugin; the Claude Code, Codex, and VS Code plugins add the server automatically. Selected Playwright tests, the data they need to run, and their results are sent to Endform, so choose what to share with that in mind.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add mcp -- npx -y endform
```

### Codex

**Platform CLI**
```bash
codex mcp add endform -- npx -y endform
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "endform": {
            "command": "npx",
            "args": [
                "-y",
                "endform"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "endform": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "endform"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add endform npx -y endform
```

## When to use it
- find inconsistent Playwright tests
- investigate a test that fails in CI
- spot slow checks in a test suite
- set aside a flaky test

## Example prompts
- Find inconsistent Playwright tests in my Endform runs.
- Investigate why the checkout test fails in CI.
- Look for slow checks and set aside the unstable search test.

## Similar
- [playwright-stealth-verify](https://affpapa.org/en/nevibecode/skills/playwright-stealth-verify.md) — skill · 132900 installs
- [momentic-result-classification](https://affpapa.org/en/nevibecode/skills/momentic-result-classification.md) — skill · 68500 installs
- [om-integration-tests](https://affpapa.org/en/nevibecode/skills/om-integration-tests.md) — skill · 3800 installs
- [playwright-testing](https://affpapa.org/en/nevibecode/skills/playwright-testing.md) — skill · 3400 installs
- [browser-trace](https://affpapa.org/en/nevibecode/skills/browser-trace.md) — skill · 3100 installs
- [access-protected-vercel-deployment](https://affpapa.org/en/nevibecode/skills/access-protected-vercel-deployment.md) — skill · 2600 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
