Home
cd ../playbooks
Sales & RevenueBeginner

Firecrawl Business Contact Finder

Find published organizational emails, phone numbers, and official contact forms for named businesses or local services, each cited to its source

10 minutes
By FirecrawlSource
#firecrawl#contacts#local-business#research#lead-lists#sourcing

Directory contact lists are full of stale emails and guessed addresses. This playbook has Claude check each business's own contact page first, return only what's actually published, cite the page, and leave the field blank when nothing was found instead of inventing a plausible address.

Who it's for: local-business researchers, procurement teams, event and booking coordinators, PR and partnerships teams, journalists, sales ops building lists of organizations

Example

"Find general contact emails and phone numbers for five independent bookstores in Portland" → a table with each business's published general or sales inbox, shared phone number, or official contact form, a source link per value, directory-sourced contacts labelled as such, and blanks where nothing was published

CLAUDE.md Template

New here? 3-minute setup guide → | Already set up? Copy the template below.

Or install from your terminal:
npx ccplaybooks add firecrawl-business-contacts
# Business contact research

**When to use:** Find published organizational emails, phone numbers, and official contact forms for named businesses or local services. Use for sourced business contacts; exclude employee direct details.

Source: https://github.com/firecrawl/firecrawl-claude-plugin/blob/main/skills/business-contact-research/SKILL.md (MIT, Firecrawl).

## Prerequisite: the Firecrawl MCP

This workflow runs on Firecrawl's hosted MCP server (tools such as `firecrawl_search` and `firecrawl_scrape`). If those tools are not available, tell the user to connect Firecrawl (in Claude Code, run `/mcp` and connect the account) instead of guessing at tools or arguments. Requests send search queries, page URLs, and any provider inputs to Firecrawl, so include only what the task needs.

1. When browsing is permitted and existing evidence is insufficient, use the Firecrawl MCP within the user's allowed sources. Read its live schemas and invoke its discovered `firecrawl_search` operation to find the requested businesses and official contact pages. Use the returned tool paths; do not construct connection identifiers or invent arguments. Tool discovery alone does not retrieve evidence; inspect the actual Firecrawl result before claiming retrieval. Reuse adequate current source content already retrieved; do not repeat a fetch solely to call a tool.
2. When browsing is permitted and the business's own website is within the allowed sources, check its contact, about, or footer page for published contact details before relying on a directory listing. Reuse adequate current official-page content already available; otherwise retrieve it with `firecrawl_scrape` using the live schema for arguments. If source restrictions prevent that check, stay within the allowed sources and disclose that official-page verification was not performed. Prefer official business sources within the permitted scope and cite each contact's source.

Get new playbooks like this one

One email a week with new Claude Code workflows. Free, like everything here.

No spam. Unsubscribe anytime.

README.md

What This Does

Finds organizational contact channels for named businesses or local services: general, sales, press, booking, or support inboxes, shared business phone numbers, and official contact forms. It deliberately excludes named employees' direct addresses and private or personal details, even if a directory publishes them.

The workflow:

  1. Find the businesses and their official contact pages with firecrawl_search within your allowed sources.
  2. Check the business's own site first (contact, about, or footer page) before relying on a directory listing. If source restrictions block that check, Claude says official-page verification wasn't performed.
  3. Return the requested fields. An email appears only if the cited page's retrieved content shows it. Contacts from directories or other third-party pages are labelled as such. A public business email and a contact form are kept distinct.
  4. Leave gaps empty. If no published value was found, the field stays empty. No "Pending verification" or "Not found" placeholders, and no addresses constructed from a name or domain pattern.

Claude doesn't send any outreach.


Before You Start

This workflow runs on Firecrawl's hosted MCP server, which gives Claude tools to search the live web and read pages. You need a Firecrawl account and a connected MCP server.

Easiest route: the Firecrawl plugin. In Claude Code:

/plugin marketplace add firecrawl/firecrawl-claude-plugin
/plugin install firecrawl@firecrawl

Then run /reload-plugins (or start a new session) and /mcp to connect your Firecrawl account. Installing the plugin and connecting the account are separate steps. The plugin bundles all thirteen Firecrawl skills, so this playbook is mainly for people who want just this one workflow as a standalone CLAUDE.md. Choose one installation of Firecrawl so the skills don't duplicate.

Cost and privacy. Web, developer, and paper searches are billed per request, page retrieval is billed per URL, and provider data uses each capability's listed price. Government search and provider discovery are free. Check your Firecrawl plan. Requests send search queries, page URLs, and any provider inputs to Firecrawl, so include only what the task needs.


Quick Start

Step 1: Create a Project Folder

mkdir -p ~/Documents/BusinessContacts

Step 2: Download the Template

Click Download above, then:

mv ~/Downloads/CLAUDE.md ~/Documents/BusinessContacts/

Step 3: Start Working

cd ~/Documents/BusinessContacts
claude

Then ask in plain language:

"Find published contact emails and phone numbers for [10 type of business] in [city]"
"Get the official press and sales contact for [Company A], [Company B], and [Company C]"
"Does [business] publish an email, or only a contact form?"

Tips & Best Practices

  • Specify location, count, and source preferences. Claude respects them, including a request not to browse.
  • Ask for the fields you need. General email, phone, contact form, or all three.
  • Treat directory-sourced contacts as lower confidence. They're labelled, so you can prioritize official-site values.
  • For individual professionals, use the leads playbooks. This one is about organizations. The enrichment and prospecting playbooks cover people.

Limitations

  • Published channels only. If a business publishes nothing, you get a blank, not a guess.
  • No employee direct details. Named employees' emails and private contact details are excluded.
  • No outreach. Claude doesn't send messages.
  • Stale pages happen. A cited page shows what was published when Claude read it. Check before a mass mailing, and follow applicable marketing and privacy rules.

$Related Playbooks

Sales & Revenue

Firecrawl Lead Enrichment

Enrich one professional or a supplied lead list or CSV with role, employer, profile, and history, with per-field sources and per-row match status

10 minutes
Intermediate
Sales & Revenue

Firecrawl Lead Finder

Find professionals matching role, company, location, or expertise criteria, with evidence of fit, profile links, and partial matches kept separate from verified ones

10 minutes
Intermediate
Sales & Revenue

GEO Proposal Generator: Turn an Audit Into a Priced Client Offer

Converts GEO audit findings into a client-ready proposal with executive summary, three priced tiers, ROI projection, timeline, and terms

10 minutes
Intermediate
Sales & Revenue

GEO Prospect Manager: A CRM for Selling AI Search Services

Tracks GEO agency leads through lead, qualified, proposal, won, and lost stages in a local JSON file, with audit scores, notes, and MRR forecasting

10 minutes
Intermediate
Sales & Revenue

Lead Qualification Framework

Score and qualify leads based on criteria and fit

10 minutes
Beginner
Sales & Revenue

Lead Routing & Assignment

Intelligent lead assignment and routing - AI-powered scoring, territory mapping, round-robin distribution, and workload balancing

10 minutes
Advanced
Sales & Revenue

WooCommerce Store Automation

Automate WooCommerce e-commerce operations including orders, inventory, customers, and marketing

10 minutes
Advanced
Sales & Revenue

Stripe Payment Integration

Automate Stripe payment processing, subscription management, invoicing, and financial reporting

10 minutes
Advanced
Sales & Revenue

Subscription Management System

SaaS subscription lifecycle management - billing, upgrades, downgrades, churn prevention, and revenue optimization

10 minutes
Advanced
Sales & Revenue

Pipeline Update

Update CRM pipeline.

15 minutes
Intermediate
Sales & Revenue

Sales Asset Creator

Generate tailored sales assets including landing pages, slide decks, and one-pagers from deal context

10 minutes
Intermediate
Sales & Revenue

Sales Call Summarizer

Process call notes and transcripts into structured summaries, action items, and follow-up emails

5 minutes
Beginner

Browse all Sales & Revenue playbooks →