Clutch.co Scraper - Agency Ratings, Reviews & Contacts

Clutch.co Company Scraper & MCP Connector

Pull verified B2B service-provider data straight off Clutch.co — agencies and dev shops across software development, web design, digital marketing, SEO, mobile app development, and IT services. No login, no manual profile-by-profile copy-pasting, no CAPTCHA-solving by hand.

Built for agencies doing competitor research, sales teams prospecting for outsourcing partners, and researchers who need Clutch's ratings, reviews, and contact data as clean, structured records — in minutes, not hours of clicking through listings.

Pick a category, name, or location → get every company's rating, pricing, reviews, and full contact/team profile → deliver it straight into Notion, Slack, Airtable, or your CRM.

---

⭐ Why This Actor?

• ✅ Three ways in — browse a full category, search by company name, or filter by location; combine name + category for a fallback search-then-browse flow.
• ✅ Deep profile enrichment — optionally visit every company's profile page for overview, about/team, portfolio, offices, verification badges, and full contact details (website, phone, email, LinkedIn, Twitter, Facebook, Instagram).
• ✅ Reviews on demand — pull the first page of reviews by default, or toggle full pagination to capture every review left on a profile.
• ✅ Concurrent enrichment — profile pages are scraped concurrently (5 at a time by default) so enrichment doesn't run one company at a time.
• ✅ Cloudflare-aware — every scrape path detects "Just a moment" interstitials and waits them out, with retry-and-backoff on failed page loads.
• ✅ Never returns messy nulls — every missing field falls back to "N/A" instead of null, so the dataset stays clean and consistent.
• ✅ Deliver anywhere via MCP connectors — push scraped companies straight into Notion, Slack, Airtable, Google Sheets, and more.
• ✅ Export-ready — JSON, CSV, Excel, JSONL, or XML, or direct API integration for your own pipeline.

---

📝 Use Cases & ROI

Use Case	Time Saved	What You Get
Outsourcing partner sourcing	3–6 hrs/search	Every agency in a category/location, ranked by rating and hourly rate, ready to shortlist
Competitor benchmarking	2–4 hrs/report	Pricing, team size, reviews, and positioning for direct competitors
Sales prospecting	3–5 hrs/list	Verified contact details (email, phone, website, socials) for cold outreach
Reputation & review analysis	2–5 hrs/scan	Full review history per company for sentiment and win/loss patterns
Market mapping	4–8 hrs/build	Structured data to power directories, comparison sites, or internal databases

---

🚀 How to Use

1. Open the Actor on Apify.
2. Pick a Category from the dropdown (e.g. Software Developers, SEO Companies), or leave it blank to scrape all categories.
3. (Optional) Enter a Filter by Name to search for a specific company by name instead of browsing a category.
4. (Optional) Enter a Location Filter using Clutch's location slug (e.g. new-york-city, india, united-kingdom).
5. Set Max Pages and Max Records to control how much of the listing to pull.
6. Toggle Scrape Profile Pages to enrich each company with full profile data, and Scrape All Reviews to paginate through every review instead of just the first page.
7. (Optional) Pick an MCP connector to deliver scraped companies into Notion, Slack, Airtable, etc.
8. Click Run — results stream into the dataset as each company is scraped.
9. Download as JSON, CSV, Excel, JSONL, or XML — or let the connector push them into your tools automatically.

💡 First time with a connector? Run once with a connector selected — the run log prints the connector's available tool names, so you know what to put in Connector tool name.

---

🧩 Input Configuration

Field	Type	Required	Description
category	Select	Optional	One of software-developers, web-designers, digital-marketing, seo-companies, mobile-app-developers, it-services. Leave blank to scrape all categories.
filterName	String	Optional	Case-insensitive substring filter. If set with no category/location, searches Clutch directly by name (falling back to a category scrape if the search returns nothing).
location	String	Optional	Clutch's URL-based location slug (e.g. new-york-city, india, united-kingdom). Leave blank to scrape globally.
maxPages	Integer	Optional	Max listing pages to paginate through. Default: 1.
maxRecords	Integer	Optional	Max total companies to collect (0 = unlimited). Default: 10.
scrapeProfiles	Boolean	Optional	Visit each company's profile page for reviews, team, portfolio, and contact data. Slower but much richer. Default: true.
scrapeAllReviews	Boolean	Optional	Paginate through every review page per profile instead of just the first ~10. Default: false.
mcpConnector	Connector	Optional	Deliver scraped companies into a connector you've authorized (Notion, Slack, Airtable, Google Sheets, …).
deliveryMode	Enum	Optional	summary (one call with the full company list), chunked (split a large list across multiple calls), perCompany (one call per company), or none. Default: summary.
mcpTool	String	Optional	Tool to call on the connector (e.g. create_page, send_message, append_row).
mcpArguments	Object	Optional	Arguments for the tool; string values support {placeholders}.
mcpMessageTemplate	String	Optional	Template rendered per delivery, exposed as the {message} placeholder.

[!TIP] Combine category with location to shortlist agencies in a specific market. Use filterName on its own to look up one company by name.

Example — Scrape a category with full profile enrichment

{
  "category": "software-developers",
  "location": "india",
  "maxPages": 3,
  "maxRecords": 50,
  "scrapeProfiles": true,
  "scrapeAllReviews": false
}

Example — Look up one company by name and post it to Slack

{
  "filterName": "Techforce Global",
  "scrapeProfiles": true,
  "mcpConnector": "<your-slack-connector>",
  "deliveryMode": "perCompany",
  "mcpTool": "send_message",
  "mcpArguments": { "channel": "#agency-leads", "text": "{message}" },
  "mcpMessageTemplate": "{name} — {rating} — {location} — {website} — {profileLink}"
}

Example — Scrape and log a summary into Notion

{
  "category": "seo-companies",
  "maxPages": 2,
  "maxRecords": 30,
  "mcpConnector": "<your-notion-connector>",
  "deliveryMode": "chunked",
  "mcpTool": "create_page",
  "mcpArguments": {
    "parent": { "page_id": "<your-page-id>" },
    "pages": [
      {
        "properties": { "title": "Clutch companies — part {part}/{partCount}" },
        "content": "{companies}"
      }
    ]
  }
}

Placeholders available in arguments / template

Summary & chunked modes: {companyCount} · {companies} · {message} Chunked mode adds: {part} · {partCount} Per-company mode: any field from that company's output record — {name} · {profileLink} · {rating} · {location} · {hourlyRate} · {minProjectSize} · {description} · {website} · {contactEmail} · {contactPhone} · {contactLinkedin} · {contactWebsite} — plus {companyText} (a formatted block) and {message}

---

📦 Output Fields

Field	Description
name	Company name
profileLink	Direct link to the company's Clutch profile
rating	Clutch rating (e.g. 4.9)
location	Primary location as shown on the listing
hourlyRate	Listed hourly rate band
minProjectSize	Minimum project size
description	Short listing description
website	Company website (from the listing/profile header)
overviewName / overviewPosition / overviewAvatar	Contact shown in the profile's overview block (profile scrape only)
employees / yearFounded / languages / timezones / reviewCount	Highlights from the profile header (profile scrape only)
languagesList	Full list of languages spoken (profile scrape only)
offices	Array of office objects: address, phone, employees, verified (profile scrape only)
contactWebsite / contactLinkedin / contactTwitter / contactFacebook / contactInstagram / contactPhone / contactEmail	Contact details from the profile's contact section (profile scrape only)
teamBio / quickFacts / teamBreakdown / tools	About/team section content (profile scrape only)
members	Array of team member objects: name, position, bio, photo (profile scrape only)
reviews	Array of scraped reviews (first page, or all pages if scrapeAllReviews is enabled) (profile scrape only)

Fields marked (profile scrape only) are only populated when scrapeProfiles is enabled; otherwise the output contains just the listing-level fields (name through website). Any field Clutch doesn't expose for a given company returns "N/A" rather than being omitted.

Example Output

{
  "name": "Techforce Global",
  "profileLink": "https://clutch.co/profile/techforce-global",
  "rating": "4.9",
  "location": "Ahmedabad, India",
  "hourlyRate": "$25 - $49 / hr",
  "minProjectSize": "$1,000+",
  "description": "Techforce Global is a web & mobile app development company...",
  "website": "https://www.techforceglobal.com",
  "employees": "50 - 249",
  "yearFounded": "2015",
  "reviewCount": "12",
  "contactWebsite": "https://www.techforceglobal.com",
  "contactEmail": "N/A",
  "contactPhone": "+91 XXXXXXXXXX",
  "offices": [
    { "address": ["Ahmedabad", "Gujarat", "India"], "phone": "N/A", "employees": "N/A", "verified": true }
  ]
}

You can download the dataset in various formats such as JSON, HTML, CSV, Excel, or XML.

---

🗺️ Supported Categories

Category value	Description	Clutch URL
software-developers	Software Developers	clutch.co/developers
web-designers	Web Designers	clutch.co/web-designers
digital-marketing	Digital Marketing	clutch.co/agencies/digital-marketing
seo-companies	SEO Companies	clutch.co/seo-firms
mobile-app-developers	Mobile App Developers	clutch.co/app-developers
it-services	IT Services	clutch.co/it-services

Leave category blank to scrape across all six.

---

🔌 Integrations & Delivery

Deliver scraped companies into any MCP connector you've authorized in Apify — no glue code, no webhooks:

• Notion — log a running page of companies (use chunked mode for large lists so Notion never times out)
• Slack / Discord — post companies or summaries to a channel as they're found
• Airtable / Google Sheets — append a structured row per company
• Jira / Linear / GitHub — open a follow-up task per company (e.g. outreach or vendor review)
• …or any other MCP-compatible connector

Credentials stay private — delivery runs through the Apify MCP Proxy, so the Actor never sees your connector tokens. You can also consume the dataset directly via the Apify API, or wire it into n8n, Zapier, and Make.

⚙️ Delivery modes: summary sends the full company list in one call, chunked splits a large list across a few calls/pages, and perCompany sends one call per scraped company. MCP delivery only runs on the Apify platform and never affects what's saved to the dataset.

🔧 Connector Tool Arguments Reference

Ready-to-paste mcpTool + mcpArguments combos for common connectors.

Slack — mcpTool: "send_message", mode perCompany or summary

{ "channel": "#agency-leads", "text": "{message}" }

Discord — mcpTool: "send_message", mode perCompany or summary

{ "channel_id": "<your-channel-id>", "content": "{message}" }

Notion — mcpTool: "create_page", mode perCompany (one page per company)

{
  "parent": { "database_id": "<your-database-id>" },
  "properties": {
    "Name": { "title": [{ "text": { "content": "{name}" } }] },
    "Rating": { "rich_text": [{ "text": { "content": "{rating}" } }] },
    "Location": { "rich_text": [{ "text": { "content": "{location}" } }] },
    "Hourly Rate": { "rich_text": [{ "text": { "content": "{hourlyRate}" } }] },
    "Website": { "url": "{website}" },
    "Profile": { "url": "{profileLink}" }
  }
}

Notion — mcpTool: "create_page", mode chunked (one page per batch of companies)

{
  "parent": { "page_id": "<your-page-id>" },
  "properties": { "title": [{ "text": { "content": "Clutch companies — part {part}/{partCount}" } }] },
  "children": [
    { "object": "block", "type": "paragraph", "paragraph": { "rich_text": [{ "text": { "content": "{companies}" } }] } }
  ]
}

Airtable — mcpTool: "create_record", mode perCompany

{
  "table": "Clutch Companies",
  "fields": {
    "Name": "{name}",
    "Rating": "{rating}",
    "Location": "{location}",
    "Hourly Rate": "{hourlyRate}",
    "Website": "{website}",
    "Email": "{contactEmail}",
    "Phone": "{contactPhone}",
    "Profile": "{profileLink}"
  }
}

Google Sheets — mcpTool: "append_row", mode perCompany

{
  "spreadsheetId": "<your-spreadsheet-id>",
  "range": "Sheet1!A:G",
  "values": [
    ["{name}", "{rating}", "{location}", "{hourlyRate}", "{website}", "{contactEmail}", "{profileLink}"]
  ]
}

Jira — mcpTool: "create_issue", mode perCompany

{
  "project": "BIZ",
  "issueType": "Task",
  "summary": "Vendor review: {name} ({location})",
  "description": "{message}"
}

Linear — mcpTool: "create_issue", mode perCompany

{
  "teamId": "<your-team-id>",
  "title": "Vendor review: {name} ({location})",
  "description": "{message}"
}

GitHub — mcpTool: "create_issue", mode perCompany

{
  "owner": "your-org",
  "repo": "vendor-tracking",
  "title": "{name} — {location}",
  "body": "{message}"
}

For the Jira / Linear / GitHub examples above, pair with this mcpMessageTemplate:

{name} — {rating} — {location} — {hourlyRate}
{website}
{profileLink}

---

🛠️ How It Works

my_actor/main.py reads the input and picks a scraping strategy:

1. If filterName is set with no category/location, it searches Clutch directly (scraper.scrape_by_name) and automatically falls back to scraping every category with the name filter applied if the search returns zero results.
2. Otherwise, it scrapes one category (or all six if category is blank) via scraper.scrape_all, paginating up to maxPages, applying location/filterName filters, and stopping once maxRecords is reached.
3. If scrapeProfiles is enabled, each company's profile page is visited concurrently (profileScraper.scrape_profile, 5 at a time by default) to pull overview, about/team, portfolio, offices, verification, contact details, and reviews — paginating every review page if scrapeAllReviews is on.
4. Every scrape path runs a stealth Playwright context (spoofed navigator.webdriver, custom user agent/locale/timezone), detects Cloudflare "Just a moment" interstitials and waits them out, and retries failed page loads with backoff.
5. Results are pushed to the dataset as they're collected, then — if a connector is configured — delivered via MCP once scraping finishes.

Built with: Apify SDK for Python · Playwright · MCP

---

🛠 Running Locally

# Install dependencies
pip install -r requirements.txt
playwright install chromium --with-deps

# Create local input file
mkdir -p storage/key_value_stores/default
echo '{
  "category": "software-developers",
  "location": "india",
  "maxPages": 1,
  "maxRecords": 10,
  "scrapeProfiles": true,
  "scrapeAllReviews": false
}' > storage/key_value_stores/default/INPUT.json

# Run the actor
python -m my_actor

---

🆘 Support

For issues, custom scraping requests, or feature suggestions: Email: bhavin.shah@techforceglobal.com

---

Need a Custom Pipeline?

Want multi-category batch runs, scheduled refreshes, deeper enrichment, or a full data-warehouse integration?

📅 Book a Free 15-min Consultation

---

Made with ❤️ by Techforce Specialists in High-Performance Web Scrapers and AI Automation.

---

Disclaimer

This Actor is an independent tool and is not affiliated with, endorsed by, or sponsored by Clutch.co. Clutch® is a trademark of its respective owner; all trademarks are property of their respective owners. The Actor collects only publicly available information (company listings, ratings, and profile data shown on public pages) and does not log into, or scrape behind the authentication of, any platform. Use the data responsibly and in compliance with applicable laws (including GDPR/CCPA) and Clutch's terms of service.