mcpField
P
playwrightselectorguard-mcp

playwrightselectorguard-mcp

Remote
github.com/clauxelBrowser Automation0Updated 23w ago
Repository

About playwrightselectorguard-mcp

playwrightselectorguard-mcp is a hosted service for assessing brittle Playwright selectors. It offers healing suggestions, action receipts, human approval requests, and failure exports for browser automation teams.

Key features

  1. 01Playwright selector risk checks
  2. 02Selector healing suggestions
  3. 03Action receipt recording
  4. 04Human approval requests
  5. 05Selector failure exports

Use cases

  1. 01Identify brittle selectors in Playwright automation
  2. 02Review suggested selector replacements
  3. 03Require human approval for an action
  4. 04Export selector failure records

MCP support

Exposes selector checks, healing suggestions, receipts, approval requests, and failure exports through a hosted remote MCP endpoint. Production requests require a bearer token and use Streamable HTTP.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://playwrightselectorguard.clauxel.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://playwrightselectorguard.clauxel.com/mcpAuth required

Tools

Details

From the project README

Playwright Selector Guard MCP

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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.