BuiltWith MCP

BuiltWith MCP

Enables AI assistants to query BuiltWith's technology detection data directly, supporting natural language questions about website technologies.

Category
Visit Server

README

πŸ” BuiltWith MCP Server πŸš€

🌟 Overview

BuiltWith MCP is a Model Context Protocol (MCP) server that allows AI assistants (Claude, Cursor, IDE agents, etc.) to query BuiltWith’s technology detection data directly and natively.

It enables natural-language questions like:

β€œWhat technologies does example.com use?” β€œDoes this site run Shopify or Magento?” β€œWhat analytics stack is used by nytimes.com?”

BuiltWith MCP supports bring-your-own BuiltWith API key and can be used either as a hosted service or self-hosted.


Claude DEMO

Shows how to get this working in Claude as a Connector

https://github.com/user-attachments/assets/1199362a-c813-497e-8569-15b9a3ce9713

🌐 Hosted MCP (Recommended)

BuiltWith provides a hosted MCP endpoint β€” no local Node process required.

Endpoint

https://api.builtwith.com/mcp

Authentication

Bring your own BuiltWith API key:

Authorization: Bearer YOUR_BUILTWITH_API_KEY

Example MCP request

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/list"
}

🧩 Supported Tools

The hosted MCP exposes the following tools:

  • domain-lookup – Live technology detection for a domain
  • domain-api – Full domain metadata
  • change-api – Technology additions and removals with business context
  • lists-api – Sites using a technology, including OTHERTECHS and numeric attribute filters such as SPEND, REVENUE, and EMPLOYEES
  • relationships-api – Related websites
  • free-api – Category and group counts
  • company-to-url – Company β†’ domain discovery
  • tags-api – IP / attribute based discovery
  • recommendations-api – Technology recommendations
  • redirects-api – Live and historical redirects
  • keywords-api – Keyword intelligence
  • trends-api – Technology trend data
  • product-api – Ecommerce product search
  • trust-api – Trust scoring
  • financial-api – Financial data
  • social-api – Social profile associations
  • vector-search – Semantic similarity search across technologies and categories
  • ask-api – Natural language website list lookup (e.g. "Magento websites in Spain"); supports full reports and pagination
  • payment-balance – Check your API credit balance
  • payment-config – Retrieve your payment configuration
  • payment-purchase – Purchase API credits using your saved Stripe payment method
  • agent-auth-start – Start Agent Device-Code Authorization (no API key required)
  • agent-auth-token – Poll for authorization result and retrieve access token (no API key required)

βš™οΈ Client Configuration (Claude, Cursor, IDEs)

Add BuiltWith MCP to your MCP-compatible client configuration.

Example

{
  "mcpServers": {
    "builtwith": {
      "url": "https://api.builtwith.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_BUILTWITH_API_KEY"
      }
    }
  }
}

Configuration locations

  • Claude Desktop

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Cursor / Claude Dev (VS Code)

    • macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
    • Windows: %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json

πŸ› οΈ Self-Hosting (Optional)

You can also run the BuiltWith MCP server locally or inside your own infrastructure.

What changed (February 14, 2026)

The local server now supports both standard MCP transports:

  • stdio (default) for local MCP clients like Claude Desktop/Cursor
  • http for remote/connector style MCP usage on /mcp

Installation

git clone https://github.com/builtwith/builtwith-mcp.git
cd builtwith-mcp
npm install

Local (stdio) MCP configuration

{
  "mcpServers": {
    "builtwith": {
      "command": "node",
      "args": ["[PATH-TO]/bw-mcp-v1.js"],
      "env": {
        "BUILTWITH_API_KEY": "YOUR_BUILTWITH_API_KEY"
      }
    }
  }
}

Note: The hosted endpoint is recommended for most users. Self-hosting is useful if you need custom routing, rate-limiting, or private network access.

Local HTTP MCP endpoint

Run in HTTP mode:

MCP_TRANSPORT=http PORT=8787 node bw-mcp-v1.js

MCP endpoint:

http://127.0.0.1:8787/mcp

Optional headers/environment:

  • Authorization: Bearer YOUR_BUILTWITH_API_KEY (per-request API key for HTTP mode)
  • BUILTWITH_API_KEY (used by stdio mode, and as fallback when no HTTP bearer token is provided)
  • MCP_ALLOWED_ORIGINS (comma-separated CORS/origin allowlist for HTTP mode)

Health check:

http://127.0.0.1:8787/health

πŸ” Agent Device-Code Authorization

Agents can obtain a temporary bw- prefixed API token without the user pasting their key β€” the user approves access in their browser.

Flow:

  1. Call agent-auth-start β†’ receive device_code and verification_uri
  2. Direct the user to open verification_uri in their browser
  3. Poll agent-auth-token every 5 seconds with the device_code
  4. On approval, receive an access_token (bw-...) valid for the chosen duration (1 hour / 1 day / 30 days)
  5. Use the token as KEY=bw-... on any BuiltWith API endpoint

No API key is required to call agent-auth-start or agent-auth-token.


πŸš€ Usage Examples

Once configured, try asking your AI assistant:

  • β€œWhat technologies is example.com using?”
  • β€œWhat CMS does nytimes.com run on?”
  • β€œDoes amazon.com use Google Analytics?”
  • β€œWhat JavaScript frameworks are used by spotify.com?”
  • β€œWhat hosting provider does netflix.com use?”
  • β€œCompare the technology stacks of facebook.com and twitter.com”

🧠 How It Works

  1. πŸ—£οΈ User asks a technology question in an AI assistant
  2. πŸ”Œ The assistant calls the BuiltWith MCP server
  3. πŸ” MCP translates intent into BuiltWith API calls
  4. πŸ“Š BuiltWith returns structured technology data
  5. πŸ’¬ The AI assistant presents human-friendly insights

πŸ“– BuiltWith API Documentation


πŸ“„ License

MIT License β€” see the LICENSE file for details.


Built for AI-native workflows by <a href="https://builtwith.com">BuiltWith</a>

Just say which.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured