MCP server for per-agent cost attribution, budget management, and spend analytics across AI agent fleets
Global stats for the Boolsai directory: how many sites are indexed, signal types covered, top vendors, most-changed companies. Use at the start of a session to ground what's available.
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
What it does
Indexed ecommerce site directory — vendor lookups, brands by city/market/founder. 10 tools.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add boolsai-directory-mcp
# 2 — ask your agent something
> Indexed ecommerce site directory — vendor lookups, brands by city/market/founder. 10 tools.
Boolsai Directory is free: there is no plan to choose, no cap to set and nothing that can bill you.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add --transport http boolsai-directory-mcp https://directory.boolsai.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Global stats for the Boolsai directory: how many sites are indexed, signal types covered, top vendors, most-changed companies. Use at the start of a session to ground what's available.
Takes no parameters.
Full intel dossier for a single domain: detected vendors grouped by category, account IDs (GTM, GA4, Klaviyo company_id, Shopify shop_id, Meta pixel, Sentry org, Tealium tenant, Stripe pk_live, etc.), brand identity (name, founder, city, employees, social handles), international markets, external host list, and likely operator-cluster siblings. Use for any 'what's running on X.com?' query.
Takes no parameters.
List indexed sites detected using a specific vendor (e.g. 'klaviyo', 'yotpo', 'elevar', 'gorgias', 'rebuy'). Vendor slug is lowercase, underscore-separated. Returns domain list with brand names where known.
Takes no parameters.
Cross-reference any tenant-unique account ID across the index. Useful for 'who else shares this GTM container / Klaviyo company / Sentry org / Meta pixel ID?'. Signal types: gtm_container, ga4_measurement, ga_ua, klaviyo_company_id, meta_pixel_id, shopify_shopid, myshopify_slug, hotjar_id, intercom_app_id, hubspot_portal, klaviyo_subscriber, tiktok_pixel, stripe_pk_live, sentry_dsn_org, tealium_te
Takes no parameters.
List indexed brands that publish a physical address in a given city. Sourced from Schema.org Organization JSON-LD.
Takes no parameters.
List indexed brands explicitly serving a country market (via hreflang). Country is a 2-letter ISO code, lowercase.
Takes no parameters.
List brands matching a stack archetype. Valid slugs: headless-shopify, classic-shopify-dtc, server-side-tagged, personalisation-heavy, pixel-stacked, multi-region, woocommerce-stores, magento-stores, bnpl-enabled, headless-cms.
Takes no parameters.
Side-by-side stack comparison of 2-5 domains. Returns each site's vendors, account IDs, brand info, markets — and which signals are shared / unique per site. Good for 'compare X.com vs Y.com' or competitive teardowns.
Takes no parameters.
Find brands with similar stack archetypes to the given domain. Returns 'sites running similar tech' — useful for benchmarking, prospecting, competitor lookups.
Takes no parameters.
List brands attributed to a founder (from Schema.org Organization markup). Useful for tracking serial DTC founders.
Takes no parameters.
Paginated bulk export of indexed sites matching a filter. Returns up to 1000 rows per page in CSV or JSONL format with a cursor for continued pages. Use this when an agency needs an outbound prospect list (e.g. all sites using Klaviyo in the US) for CRM import. The full row count is also returned so you can size the export.
Takes no parameters.
Compare two historical scans of the same URL to surface stack changes. Returns added/removed/changed vendors, account IDs, and inline-script signals between scan A and scan B. Use this for competitor watch — 'what did patagonia.com just deploy?'. If t1/t2 are omitted, compares oldest vs newest available scan.
Takes no parameters.
Free DNS/WHOIS enrichment for a single domain. Returns: email host (Google Workspace / Microsoft 365 / etc. — derived from MX records), DNS provider (Cloudflare / Route 53 / GoDaddy / etc.), CDN provider, registrar, domain age (registered/expires). High-signal outbound data — 'they use Google Workspace + Cloudflare DNS + registered with GoDaddy' tells you a lot about org size + sophistication. Res
Takes no parameters.
Find sites with the most-similar vendor stack to a given domain using Jaccard similarity over the full vendor set (not just archetype labels). Returns the top N matches with similarity scores. Use this when stack_archetype labels are too coarse and you want 'show me 20 brands running an almost-identical stack to liquiddeath.com'. More accurate than similar_sites for niche stacks.
Takes no parameters.
Returns a streaming-export URL for the same filter as bulk_export. Useful when the agency wants to pull 50K rows in one shot via curl/HTTP pipe instead of paginating the MCP. The URL is public, no auth, returns NDJSON or CSV with HTTP chunked-transfer streaming. Use bulk_export when N<1000; use this for bigger exports.
Takes no parameters.
Find every domain sharing a tenant-unique ID — the most powerful single signal in Boolsai. Given a Stripe pk_live key, Sentry DSN org, Klaviyo company_id, mParticle workspace, GTM container, GA4 measurement, Shopify shop_id, or other tenant ID, returns every domain we've seen using the SAME ID. This surfaces multi-brand operators, holding-company portfolios, sister brands sharing infrastructure, a
Takes no parameters.
Every subdomain of a given root domain we've ever scanned. Reveals storefront topology — where the checkout actually lives, regional storefronts, B2B portals, internal admin domains, asset CDNs. Output groups subdomains by their primary vendor where known. Use this to (a) find the right path to scan for an audit (sometimes the checkout is on us.checkout.brand.com not brand.com), (b) spot enterpris
Takes no parameters.
ONE-CALL PROSPECT BRIEF for agency outbound — runs four sub-queries against the live indexed data: (1) full dossier of the prospect's stack, (2) sister brands sharing tenant IDs (operator cluster), (3) 3-5 similar-stack competitors, (4) structured 'pitch angles' calling out concrete gaps an agency could pitch on (missing consent, no SST, outdated vendors, broken Schema.org, multiple GTM installs).
Takes no parameters.
Unified query against the Boolsai Directory. One tool to rule the other lookups. Pass any combination of: signal_type+signal_value, domain, market_country, archetype, founder, city. Returns matching sites + their key signals. Prefer this over the granular tools when you have multiple filter conditions to AND together.
Takes no parameters.
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Boolsai Directory costs nothing to install and nothing to call, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 1.0.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
No release note was published with this version.
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Writing one takes an account with at least 50 real tool calls against Boolsai Directory in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.