Secure Privacy MCP Server
Enables AI agents to install GDPR-compliant cookie consent banners on websites with a single command, handling domain registration, template assignment, and script injection.
README
Secure Privacy MCP Server
A remote Model Context Protocol (MCP) server that enables AI agents like Claude Desktop, GitHub Copilot, and Cursor to automatically integrate GDPR-compliant cookie consent banners into websites with a single command.
Built on Cloudflare Workers, this MCP server provides a one-click solution for implementing Secure Privacy's cookie consent management platform, handling domain registration, template assignment, and script injection seamlessly.
What is MCP?
The Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect to external tools and data sources. It allows AI agents to perform actions on your behalf, making complex multi-step workflows as simple as a single conversational request.
Key Features
- One-Click Installation: Fully automate cookie banner deployment with a single AI command
- GDPR Compliant: Automatically configure compliant consent management
- Multiple Consent Modes: Support for Google Consent Mode (GCM), Microsoft UET, Meta, and more
- Template Management: Auto-assign all available cookie banner templates
- No API Key Required: Users don't need to provide any credentials
- AI Agent Compatible: Works with Claude Desktop, GitHub Copilot, Cursor, and other MCP clients
Available Tools
install_secure_privacy_banner
Fully install Secure Privacy cookie banner on a website in one step. This is the primary tool that orchestrates the entire installation process.
What it does:
- Registers a domain with Secure Privacy
- Assigns templates - Fetches and assigns all available cookie banner templates (design + functional)
- Generates the script tag - Creates the integration code for your website
- Configures consent modes - Sets up Google Consent Mode (GCM), Microsoft UET, Meta, and more
Response includes:
- Domain URL registered
- Domain ID for tracking
- Number of templates assigned
- Script tag for integration
- Confirmation of GDPR compliance
Example Usage
Simply ask your AI agent in natural language:
"Add a cookie banner to my website"
"Make my site GDPR compliant"
"Install Secure Privacy on my website"
"I need cookie consent management"
The AI will automatically use the Secure Privacy MCP to set everything up and provide you with the script tag to add to your website.
Installation
Claude Desktop
-
Install the mcp-remote proxy:
npm install -g mcp-remote -
Open Claude Desktop and go to Settings > Developer > Edit Config
-
Add this configuration:
{ "mcpServers": { "secure-privacy": { "command": "npx", "args": [ "mcp-remote", "https://mcp.secureprivacy.ai/sse" ] } } } -
Restart Claude Desktop
-
Start using it! Ask Claude: "Add a cookie banner to my website"
GitHub Copilot (VS Code)
-
Install the mcp-remote package globally:
npm install -g mcp-remote -
Open VS Code Settings (JSON) and add the MCP configuration:
{ "github.copilot.chat.mcp.servers": { "secure-privacy": { "command": "npx", "args": [ "mcp-remote", "https://mcp.secureprivacy.ai/sse" ] } } } -
Restart VS Code
-
Use Copilot Chat and ask: "Add Secure Privacy cookie banner to my site"
Cursor
-
Install the mcp-remote proxy:
npm install -g mcp-remote -
Open Cursor Settings and navigate to the MCP configuration
-
Add the Secure Privacy MCP server:
{ "mcpServers": { "secure-privacy": { "command": "npx", "args": [ "mcp-remote", "https://mcp.secureprivacy.ai/sse" ] } } } -
Restart Cursor
-
Chat with the AI and request: "Install cookie consent on my website"
Troubleshooting
Connection Issues
If the MCP server doesn't appear in your AI client:
- Verify the URL is correct:
https://mcp.secureprivacy.ai/sse - Restart your AI client after updating the configuration
- Check that
mcp-remoteis properly installed by running:npm list -g mcp-remote - Make sure you have an active internet connection
MCP Not Showing Up
- Ensure the configuration file syntax is correct (valid JSON)
- Check for typos in the server URL
- Try reinstalling
mcp-remote:npm install -g mcp-remote - Verify your AI client supports MCP (check version requirements)
Script Already Exists
If you see a message that the script is already present, that's normal! The MCP automatically detects existing Secure Privacy installations and won't duplicate the script tag.
Development
Get Started
Deploy to Cloudflare Workers:
Or use the command line:
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
Customizing the MCP Server
To add your own tools to the MCP server, define each tool inside the init() method of src/index.ts using this.server.tool(...).
Testing with Cloudflare AI Playground
You can test your MCP server from the Cloudflare AI Playground:
- Go to https://playground.ai.cloudflare.com/
- Enter your deployed MCP server URL (
mcp.secureprivacy.ai/sse) - Use your MCP tools directly from the playground
Need Help?
For additional support:
- Secure Privacy Support: Contact support
- Documentation: Browse our docs
- Email: support@secureprivacy.ai
License
See LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.