Back to resources

MCP SERVER

Boolsai Scan

Primary machine endpointhttps://boolsai.ai/mcp
Use with an agent

SUMMARY

What it does

Boolsai Scan is an MCP server that performs live tech-stack scans of public websites. It exposes two tools: boolsai_scan, which scans a single URL and returns structured JSON describing external hosts, fetch/xhr/beacon endpoints, inline-script signals, parsed JSON-LD, and an internal DOM/route trie; and boolsai_scan_paths, which scans multiple paths on the same site in parallel and merges external-host lists, useful for e-commerce audits where the homepage understates the stack. The server is available via streamable HTTP at https://boolsai.ai/mcp. The source repository is public on GitHub. No authentication or pricing details are provided in the evidence.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

data.readweight 90 · confidence 90data.analyzeweight 80 · confidence 80

TOOLS IN THIS MCP SERVER

Tools exposed by this MCP server

boolsai_scanScan a website

Scan a public website. Returns its full tech stack — every external host the page talks to, every fetch/xhr/beacon endpoint, every inline-script signal, parsed JSON-LD, and the internal DOM/route trie — as structured JSON. Hostnames are returned raw; recognise vendors from them using your own knowledge.

Effect: unknownConfirm: none
boolsai_scan_pathsScan multiple paths on a site

Scan multiple paths on the same site in parallel and merge the external-host lists. Returns per-path host lists, a unified merged set, and a homepage_missed list (hosts that appeared ONLY on non-home paths). Use when the homepage understates the stack — common on Shopify Plus and consent-gated sites where pixels lazy-load on PDP / cart / checkout. Recommended for ecom audits: paths = ["/", "/products/<any>", "/cart", "/checkout"]. Max 5 paths per call.

Effect: unknownConfirm: none

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
mcp
Authentication
type: unknown
Pricing
model: unknown
Version
1.0.0

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.