Company Contact Details Extractor MCP Server is an MCP (Model Context Protocol) server used to find a company's contact page from its domain and extract role email addresses, a primary phone number, and a mailing address. It wraps the Mamba Labs Company Contact Details Extractor actor on Apify and returns Clay-ready flat JSON rows to any MCP client.
Purpose: Given a company domain, the tool finds the company's contact page, then returns the role email addresses published on the page, a primary phone number in E.164 format (when the country can be resolved), and a mailing address. One flat row of data per company.
Key capabilities:
- Returns only role email addresses, never specific individual names. An address is retained only when the domain belongs to the company and the local part is in the role vocabulary, for example info@, support@, sales@, and privacy@ pass, while personal addresses are dropped via an allow list rather than a name detector.
- The row reports how many addresses were found and how many were rejected and why, so sparse results are not mistaken for the site publishing nothing.
- Returns the primary phone number and mailing address when the company publishes them.
- Returns the contact page URL and how that page was discovered.
- Provides rejection statistics in emails_rejected_reasons.
- Reports coverage per row.
- 27 flat snake_case fields, one row per company.
How to use:
- Requires Node.js 18 or higher and an Apify account with an API token.
- Add the configuration to the Claude Desktop config, from https://console.apify.com/account/integrations get a token and paste it, then restart Claude Desktop. The extract_company_contact_details tool will be available.
- Tool parameters:
- company_domain (required): the bare company domain, for example stripe.com. This is the lookup key and the join key for every other actor in the suite. If missing, the tool returns an error indicating the field before any run starts.
- company_name (optional): used in rows and logs. This tool gates addresses based on the email domain rather than the company name, so providing a name does not change which addresses are retained.
- emailTypes (optional): which categories of role addresses to return. Options are all, general, support, sales, privacy, general_support, or sales_only. all is the default, returning general, support, sales, and privacy. A narrower setting returns only what it names and leaves the other columns empty, which is a different answer from not found.
- includePhones (optional): when true (default), scans the contact page for a primary phone number. Set to false to skip phone extraction entirely.
- includeAddress (optional): when true (default), reads the mailing address first from JSON-LD, then from the footer. Set to false to skip.
- allowFreeMailboxes (optional): when false (default), addresses from Gmail, Outlook, or other free providers are rejected because they cannot be checked against the company domain. Set to true for small businesses and local company listings, where a free mailbox on the contact page is often a real contact point.
- crawlDepth (optional): how many pages to read after the home page. 1 (default) reads the contact page. 2 also reads support or legal pages when the contact page yields no results. This is a cost and thoroughness adjustment, not a change in the answer.
- skipCache (optional): when false (default), successful lookups are cached for seven days and reused. Set to true to force a fresh fetch.
- How invocation runs: the tool starts the actor run and polls until completion, so long runs will not time out at 300 secondswas cut off. The run is allowed 1800 seconds. If it is still running two minutes after that, call stop waiting and return the run ID and the link in the Apify Console, where the results will land once it completes. Unsuccessful runs are returned as errors, with the run ID and status.
- The tool returns flat JSON lines from that company's actor, containing 27 snake_case fields, with no nested objects. emails_rejected_count and emails_rejected_reasons explain what was discarded, contact_page_method explains how the contact page was found, and fetch_status explains whether the read succeeded.
Use cases:
- Find company contact information, for example "Find the contact details for stripe.com."
- Get a specific role's email, for example "Get figma.com's sales email and skip phone numbers."
- Extract contact details for a local business and allow free email addresses, for example "Extract this local plumbing company's contact details and allow free email addresses."
- Extract a support address and read the second page when the contact page has no content, for example "Extract notion.com's support address, and if the contact page has no content, read the second page."
Limitations:
- Requires Node.js 18 or later and an Apify account with an API token.
- All extraction runs on Apify. This package is a thin client that calls the actor and returns the results as-is.
- This server is a thin client and does not hold the extraction logic. For the full input and output reference, pricing, and run history, see the Apify Store page:https://apify.com/mambalabs/company-contact-details-extractor
- This server is one of the Mamba Labs GTM Suite MCP servers. Each actor in the suite accepts a domain or company and returns a single row of flat data, so they can be stacked in the same Clay table without reshaping anything. The actor behind this server is Company Contact Details Extractor, immutable Apify actor ID 4mMncKaJykiq94grz.
- Built by Mamba Labs.https://apify.com/mambalabs
