Playwright Selector Guard MCP

MCP serverWeb & browsing

Playwright selector risk checks with healing suggestions and receipts.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use Playwright Selector Guard MCP

From the project's README

As published by clauxel/playwright-selector-guard-mcp in README.md.

Detect brittle Playwright selectors and route safe healing suggestions.

Paid remote MCP for Playwright selector risk checks, healing suggestions, action receipts, human approvals, and failure exports.

Public Endpoints

Access

This is a paid hosted remote MCP. Production calls require a bearer token issued from the product website.

Authorization: Bearer <token>

Unauthenticated browser visits to /mcp return a clear JSON error instead of internal details.

Tools

  • check_selector_risk
  • suggest_selector_healing
  • record_action_receipt
  • request_human_approval
  • export_selector_failure

Quick Start

  1. Open the website and choose a plan.
  2. Create or request an API token.
  3. Add the endpoint to an MCP client that supports Streamable HTTP remote servers.
  4. Send JSON-RPC requests with the bearer token.

Useful Links

Status

This repository is a public documentation and directory-submission reference for the hosted service. It does not contain the private production source code.

Signals

Last commit
May 2026
Advanced
Delivery
playwrightselectorguard-mcp MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
com-clauxel-playwrightselectorguard-playwrightselect-0unlhjk
Source
github.com/clauxel/playwright-selector-guard-mcp
Hosted endpoint
https://playwrightselectorguard.clauxel.com/mcp