Summary
Gives you regex search across Boolsai's entire corpus of ecommerce tech stack scans stored in R2. Four tools: `grep_pattern` for raw regex matches, `count_pattern` for frequency analysis, `sites_with_signal` to find which domains contain a specific pattern, and `list_signal_types` to see what's indexed. Useful when you need to discover new vendor fingerprints, hunt for leaked account IDs, or spot niche tracking pixels that aren't pre-indexed in the Directory server. Runs parallel searches across hundreds of thousands of historical scans. No auth required, connects via streamable HTTP. Part of the four-server Boolsai suite but works standalone if you just need pattern matching across live commerce site data.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
1 tools
searchGitHubFind real-world code examples from over a million public GitHub repositories to help answer programming questions. **IMPORTANT: This tool searches for literal code patterns (like grep), not keywords. Search for actual code that would appear in files:** - ✅ Good: 'useState(', '...7 params
Find real-world code examples from over a million public GitHub repositories to help answer programming questions. **IMPORTANT: This tool searches for literal code patterns (like grep), not keywords. Search for actual code that would appear in files:** - ✅ Good: 'useState(', '...
Parameters* required
pathstringFilter by file path.
Examples: 'src/components/Button.tsx', 'README.md'.
Can match partial paths, for example '/route.ts' will find route.ts files at any level.
repostringFilter by repository.
Examples: 'facebook/react', 'microsoft/vscode', 'vercel/ai'.
Can match partial names, for example 'vercel/' will find repositories in the vercel org.
querystringThe literal code pattern to search for (e.g., 'useState(', 'export function'). Use actual code that would appear in files, not keywords or questions.
languagearrayFilter by programming language.
Examples: ['TypeScript', 'TSX'], ['JavaScript'], ['Python'], ['Java'], ['C#'], ['Markdown'], ['YAML']
matchCasebooleanWhether the search should be case sensitivedefault: false
useRegexpbooleanWhether to interpret the query as a regular expressiondefault: false
matchWholeWordsbooleanWhether to match whole words onlydefault: false
Boolsai — MCP server suite
Stack-intelligence MCPs for AI agents. Live, no-auth, public access to every commerce site's tech stack — every vendor, every account ID, every inline script signature, plus a quant-research signal layer on top.
Built for AI agents doing competitive intel, agency prospect research, ecommerce due diligence, and ad-hoc commerce-data discovery.
This repo contains the Anthropic MCP Registry manifests for the four-server Boolsai suite. The actual servers live at *.boolsai.ai.
The four servers
| Server | Connect URL | Tools | What it does |
|---|---|---|---|
| Boolsai Scan | https://boolsai.ai/mcp | boolsai_scan, boolsai_scan_paths | Live tech-stack scan of any public site. Returns every external host, inline script signature, route, vendor, account ID, and JSON-LD organisation block in one response. |
| Boolsai Directory | https://directory.boolsai.ai/mcp | summary, site_dossier, sites_using_vendor, lookup_id, brands_in_city, brands_in_market, stack_archetype, compare_sites, similar_sites, brands_by_founder | Pre-indexed directory of tens of thousands of ecommerce sites by vendor, account ID, country, founder, city, archetype. |
| Boolsai Grep | https://grep.boolsai.ai/mcp | grep_pattern, count_pattern, sites_with_signal, list_signal_types | Parallel regex search across the R2 corpus of every scan we've ever taken. Use when a signal isn't pre-indexed — discover new vendor patterns, leaked account IDs, niche tracking pixels. |
| Boolsai Signals | https://signals.boolsai.ai/mcp | universe_summary, find_signals, test_filter, recent_events, event_dossier, scan_at_date, ticker_history | Quant-research MCP. Hunts for tradeable signals in 316 public-company website stack changes (1,761 events), SPY-benchmarked. Wayback Machine integration. Methodology baked into the initialize response. |
Each server is independently published to the Anthropic MCP Registry under the ai.boolsai/* namespace (DNS-verified via boolsai.ai).
Why Boolsai
- No auth, no key, no rate limit gymnastics. Paste a URL into Claude.ai → Settings → Connectors. Done.
- First-party data. Every scan runs live on demand. No third-party feeds, no stale catalogue.
- Built for AI consumption. Each server's
initializeresponse includes a detailedinstructionsblock — vendor recognition tips, output schemas, methodology. Agents don't have to guess. - Suite, not silo. Cross-discovery: each server's instructions reference the other three so agents can chain queries (scan → look up in directory → grep historical → test as signal).
Install
Claude Desktop / Claude Code / Cursor
{
"mcpServers": {
"boolsai-scan": { "url": "https://boolsai.ai/mcp" },
"boolsai-directory": { "url": "https://directory.boolsai.ai/mcp" },
"boolsai-grep": { "url": "https://grep.boolsai.ai/mcp" },
"boolsai-signals": { "url": "https://signals.boolsai.ai/mcp" }
}
}
Restart the client. All four servers show up with their tools.
ChatGPT / Claude.ai Custom Connectors
Settings → Connectors → Add custom connector → paste any of the four URLs above. Add all four for the full suite.
One-liner test from a terminal
curl -sS https://boolsai.ai/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | jq .
Example agent prompts
"What's the full tech stack of gymshark.com?" →
boolsai_scan({ url: "https://gymshark.com" })
"List ten stores using Klaviyo with their company IDs." →
boolsai-directory.sites_using_vendor({ vendor: "klaviyo" })
"Show me sites with
window._fs_org(FullStory) in their inline scripts." →boolsai-grep.sites_with_signal({ pattern: "window._fs_org" })
"Find the highest-α tradeable signal in the last 30 days with n ≥ 20." →
boolsai-signals.find_signals({ horizon_days: 30, min_n: 20 })
Architecture
┌──────────────────────────┐
│ AI agent (Claude / etc) │
└────────────┬─────────────┘
│ JSON-RPC 2.0 (Streamable HTTP)
┌───────────────────┼─────────────────────┐
▼ ▼ ▼
boolsai.ai/mcp directory.boolsai.ai/mcp grep.boolsai.ai/mcp
(live scanner) (indexed corpus query) (raw R2 search)
│ │ │
│ │ │
▼ ▼ ▼
┌──────────────────────────────────────────────────────┐
│ R2 corpus (hundreds of thousands of historical scans) │
└──────────────────────────────────────────────────────┘
▲
│ derived
signals.boolsai.ai/mcp (quant signals from stack changes)
All four servers run on Cloudflare Workers with R2 for the historical corpus.
Publishing to the MCP Registry
See PUBLISHING.md for the one-time DNS verification + per-server publish commands.
License
MIT — see LICENSE.
Built by Boolsai · Contact: founder@boolsai.ai
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →