Autoconsent MCP
Requires Node.js runtime (version 18 or higher) to execute the MCP server
Uses npm for package management and running scripts to build, test, and start the server
Built on Puppeteer to provide browser automation capabilities for interacting with web pages, inspecting consent management platforms, and testing Autoconsent rules
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Autoconsent MCP test the consent popup rule on https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Autoconsent MCP
A Model Context Protocol server that provides browser automation capabilities specifically designed for creating and testing Autoconsent rules. This server enables LLMs to interact with web pages, inspect consent management platforms (CMPs), and test Autoconsent rules in a real browser environment.
This server can access local files and local/internal IP addresses since it runs a browser on your machine. Exercise caution when using this MCP server to ensure this does not expose any sensitive data.
Components
Tools
navigate
Navigate to any URL in the browser
Inputs:
url(string, required): URL to navigate to
screenshot
Capture screenshots of the entire page or specific elements
Inputs:
name(string, required): Name for the screenshotwidth(number, optional, default: 1280): Screenshot widthheight(number, optional, default: 720): Screenshot heightencoded(boolean, optional): If true, capture the screenshot as a base64-encoded data URI (as text) instead of binary image content. Default false.
click
Click elements on the page
Input:
selector(string): CSS selector for element to click
select
Select an element with SELECT tag
Inputs:
selector(string): CSS selector for element to selectvalue(string): Value to select
evaluate
Execute JavaScript in the browser console
Input:
script(string): JavaScript code to execute
search_html
Outputs the HTML of elements that deeply contain the given search query. Elements that don't contain the given query are omitted using a [...] placeholder.
Input:
query(string): Search query
print_element
Outputs the full HTML of the given element
Input:
selector(string): CSS selector
test_rule
Tests the given Autoconsent rule on the given URL
Inputs:
url(string, required): URL to navigate torule(object, required): Autoconsent rule (AutoConsentCMPRule)
Resources
The server provides access to two types of resources:
Console Logs (
console://logs)Browser console output in text format
Includes all console messages from the browser
Screenshots (
screenshot://)PNG images of captured screenshots
Accessible via the screenshot name specified during capture
Related MCP server: Puppeteer MCP Server
Installation and Setup
Prerequisites
Node.js (version 18 or higher)
npm
Setup
npm install
npm run buildRunning the Server
For development:
npm run devFor production:
npm startTest Site
npm run serve-test-siteThis starts a local HTTP server on port 8080 serving the test-site directory.
Testing
npm run test:unit
npm run test:integrationNote that the integration tests require the test site to be running (see above).
Configuration for Claude Desktop
Add the following to your Claude Desktop configuration:
{
"mcpServers": {
"autoconsent-mcp": {
"command": "node",
"args": ["path/to/autoconsent-mcp/dist/index.js"]
}
}
}Attribution and license
This project is based on the Puppeteer MCP server from https://github.com/modelcontextprotocol/servers-archived/tree/main/src/puppeteer.
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.
Available Tools
10 toolsclickC
Click elements on the page
Inputs: selector (required).
evaluateC
Execute JavaScript in the browser console
Inputs: script (required).
print_elementB
Outputs the full HTML of the given element
Inputs: selector (required).
reloadB
Reload the current page
Inputs: no named parameters.
reset_browser_dataC
Reset browser data including cookies, cache, localStorage, and sessionStorage
Inputs: clearCookies, clearCache, clearLocalStorage, clearSessionStorage.
screenshotC
Capture screenshots of the entire page or specific elements
Inputs: name (required), width, height, encoded.
search_htmlA
Outputs the HTML of elements that deeply contain the given search query. Elements that don't contain the given query are omitted using a [...] placeholder.
Inputs: query (required).
selectC
Select an element with SELECT tag
Inputs: selector (required), value (required).
test_ruleC
Tests the given Autoconsent rule on the given URL
Inputs: url (required), rule (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools have distinct purposes, but 'evaluate' and 'test_rule' could be confused as both involve executing code or rules in the browser context. The other tools like 'click', 'navigate', and 'screenshot' are clearly differentiated by their specific actions on web pages.
The naming is mixed with some tools using verb_noun patterns like 'print_element' and 'search_html', while others are single verbs like 'click' and 'reload'. There is no consistent convention across all tools, but the names are generally readable and descriptive of their functions.
With 10 tools, the count is well-scoped for a browser automation and testing server. Each tool appears to serve a specific purpose in interacting with web pages, such as navigation, element manipulation, and data resetting, making the set comprehensive without being overwhelming.
The toolset covers core browser automation tasks like navigation, interaction, and inspection, with notable tools for Autoconsent-specific testing. A minor gap is the lack of tools for handling pop-ups or alerts, which are common in consent management scenarios, but agents can work around this using existing tools like 'click' or 'evaluate'.
Related MCP Connectors
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
A Model Context Protocol server for Wix AI tools
Browser automation MCP for whole web tasks in a cloud browser: saved logins, bot checks, replays.
MCP server for Mint — AI-powered QA that runs your app in a real browser on every PR.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.19Apache 2.0
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides browser automation capabilities using Puppeteer, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.71MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables LLMs to interact with web pages, take screenshots, generate test code, scrape web pages, and execute JavaScript in a real browser environment.2922MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without requiring screenshots or vision models.221Apache 2.0