Atlas / MCP servers / builtwith / BuiltWith

BuiltWithSAFE

mcp/builtwith/builtwith-1

BuiltWith MCP Server

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
13 12r · 1w · 0d
Transport
stdio · streamable-http
License
MIT
Stars
41
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Domain API v25

Domain lookups now use API v25. Technology records include numeric confidence scores from 0 to 1. Full JSON responses include Meta.company_reg, an array of company registration records with string type and number fields; registration numbers preserve leading zeros. The array is empty when unavailable or metadata is excluded. See the API reference. Full domain methods preserve both fields; live technology lookups include confidence and return technology records only.

🌟 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:

“What technologies does example.com use?” “Does this site run Shopify or Magento?” “What 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 — 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
Read from source at commit a0fb0c20668fOBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-server --env BUILTWITH_API_KEY=${BUILTWITH_API_KEY} -- npx -y @builtwith/[email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@builtwith/[email protected]"
      ],
      "env": {
        "BUILTWITH_API_KEY": "${BUILTWITH_API_KEY}"
      }
    }
  }
}
03

Exposed tools (13)

12 read · 1 write · 0 destructive.

ToolRiskDescription
agent-auth-startwriteStart the Agent Device-Code Authorization flow. Returns a device_code and verification_uri. Direct the user to open the verification_uri in their browser to approve access. Then poll agent-auth-token every 5 seconds until approved or denied.
agent-auth-tokenreadPoll for the result of an Agent Device-Code Authorization flow. Call every 5 seconds after agent-auth-start. Returns { access_token, token_type, expires_in } on approval, { error:
analyze-tech-stackreadAnalyze the technology stack of a domain
ask-apireadAsk API lookup for natural language website list queries. OpenAI requests are served as preview results and do not commit full reports.
check-domain-trustreadCheck the trust score of a domain
discover-technologies-by-conceptreadSearch for technologies matching a concept, then explore adoption
domain-lookupreadReturns the live web technologies used on the root domain name, including v25 confidence scores.
find-related-websitesreadFind websites related to a domain
get-technology-recommendationsreadGet technology recommendations for a domain
payment-balancereadCheck your BuiltWith Agent Payment API credit balance. Returns credits_total, credits_used, and credits_available.
payment-configreadRetrieve your BuiltWith Agent Payment API configuration. Returns max_per_purchase, max_monthly, monthly_purchased, monthly_remaining, and cost_per_2000_credits_usd.
payment-purchasereadPurchase BuiltWith API credits using your saved Stripe payment method. Minimum 2,000 credits per purchase. Returns success, credits_purchased, cost_usd, payment_id, and credits_available.
research-companyreadResearch a company
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (4 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (5)

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
bw-mcp-v1.js:838
console.error(`BuiltWith MCP (HTTP) listening on http://127.0.0.1:${port}/mcp`);
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:171
http://127.0.0.1:8787/mcp
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:183
http://127.0.0.1:8787/health
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, express, zod
Why it matters. 3 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:87
* `agent-auth-token` – Poll for authorization result and retrieve access token (no API key required)
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha a0fb0c20668ffull audit observations/trust-audit/mcp-server/builtwith__builtwith-1.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08a0fb0c20668fSAFEB89first audit
06

Questions

What is the BuiltWith MCP server?

BuiltWith MCP Server

What tools does BuiltWith expose?

13 in total: 12 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is BuiltWith safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does BuiltWith need?

It reads BUILTWITH_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does BuiltWith run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @builtwith/mcp-server at 1.12.0.

How current is this page?

The grade is for one exact copy of the source (a0fb0c20668f), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement