Autoconsent

Provides browser automation to test Autoconsent rules against CMPs in a real browser environment.
  • typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "noisysocks-autoconsent-mcp": {
      "command": "node",
      "args": [
        "path/to/autoconsent-mcp/dist/index.js"
      ]
    }
  }
}

Autoconsent MCP is a Model Context Protocol server that runs a real browser to help you create, inspect, and test Autoconsent rules against CMPs. It enables LLM-driven browser automation for navigating pages, capturing state, and validating rule behavior in a safe, local environment.

How to use

You interact with Autoconsent MCP through a client that communicates with the server to perform browser actions. Use it to load web pages, explore permission prompts, test Autoconsent rules, and verify outcomes with screenshots and console logs.

How to install

Prerequisites you need before starting are Node.js version 18 or higher and npm.

Step by step install and run flow you should follow:

  • Install dependencies
  • Build the MCP package
  • Run the server

Additional sections

Configuration and runtime details are provided to help you integrate Autoconsent MCP with your workflow. You can run the server locally and connect a client to exercise Autoconsent rules in a real browser.

Security note: This server can access local files and internal IP addresses because it runs a browser on your machine. Exercise caution to avoid exposing sensitive data.

The following configuration snippet shows how to run the MCP server locally via a standard Node command.

{
  "mcpServers": {
    "autoconsent-mcp": {
      "command": "node",
      "args": ["path/to/autoconsent-mcp/dist/index.js"]
    }
  }
}

Available tools

navigate

Navigate to a URL in the browser by supplying a string URL.

screenshot

Capture a screenshot of the full page or specific elements with optional size and encoding parameters.

click

Click on a page element selected by a CSS selector.

select

Choose a value from a SELECT tag using a CSS selector and the desired value.

evaluate

Run JavaScript in the browser context and return the result.

search_html

Return HTML snippets containing a specific query, with non-matching parts replaced.

print_element

Return the full HTML of a selected element via a CSS selector.

test_rule

Test a given Autoconsent rule against a specified URL.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational