mcpField
B
Boolsai Grep

Boolsai Grep

Remote
github.com/Boolsai-aiBusiness & Marketing1Updated 23w ago
Repository

About Boolsai Grep

Boolsai Grep is an MCP server for AI agents and researchers who need to search historical website scans. It runs parallel regex queries across the scan corpus to find patterns that are not pre-indexed, including vendor signatures and account IDs.

Key features

  1. 01Parallel regex searches
  2. 02Count pattern matches
  3. 03Find sites with a signal
  4. 04List available signal types

Use cases

  1. 01Discover vendor patterns absent from indexes
  2. 02Find sites containing account ID signatures

MCP support

Exposes four pattern-search tools to MCP clients, querying the historical R2 corpus of scans.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://grep.boolsai.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Boolsai — MCP server suite

MCP License: MIT No-auth

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

ServerConnect URLToolsWhat it does
Boolsai Scanhttps://boolsai.ai/mcpboolsai_scan, boolsai_scan_pathsLive 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 Directoryhttps://directory.boolsai.ai/mcpsummary, site_dossier, sites_using_vendor, lookup_id, brands_in_city, brands_in_market, stack_archetype, compare_sites, similar_sites, brands_by_founderPre-indexed directory of tens of thousands of ecommerce sites by vendor, account ID, country, founder, city, archetype.
Boolsai Grephttps://grep.boolsai.ai/mcpgrep_pattern, count_pattern, sites_with_signal, list_signal_typesParallel 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 Signalshttps://signals.boolsai.ai/mcpuniverse_summary, find_signals, test_filter, recent_events, event_dossier, scan_at_date, ticker_historyQuant-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 initialize response includes a detailed instructions block — 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: [email protected]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.