Pricing

Pay per event + usage

Contact Finder MCP Server

MCP server for SDR agents to find public emails, phone numbers, and social profiles from company domains using focused tool calls.

Pricing

Pay per event + usage

Rating

0.0

(0)

Developer

Stas Persiianenko

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

What does Contact Finder MCP Server do?

It scans a company website and returns a compact contact result that an AI agent can use immediately.

find_emails(domain, max_pages?) returns public email addresses.
find_phones(domain, max_pages?) returns discovered phone numbers with normalized digits.
find_socials(domain, max_pages?) returns LinkedIn, X/Twitter, Facebook, Instagram, YouTube, GitHub, and TikTok URLs when found.

Who is it for?

SDR agents that need a contact step inside a prospecting workflow.
RevOps teams building lead enrichment assistants.
Founders validating small lead lists from domains.
Agencies that want an MCP tool rather than a bulk scraping UI.
Developers testing Apify Standby actors as MCP servers.

Why use this actor?

Most contact finders are batch jobs. This actor is designed around agent tool calls. Your assistant can decide which contact signal it needs, call one tool, and receive JSON that fits naturally into a chat or workflow memory.

MCP tools

Tool	Purpose	Main output
`find_emails`	Find public emails from a website and likely contact pages	`emails`
`find_phones`	Find website phone numbers	`phones`
`find_socials`	Find social media profile links	`socials`

Add it to Claude Code with:

claude mcp add apify-contact-finder \
  https://mcp.apify.com/?tools=automation-lab/contact-finder-mcp

Or configure an MCP client with JSON:

{
  "mcpServers": {
    "apify-contact-finder": {
      "url": "https://mcp.apify.com/?tools=automation-lab/contact-finder-mcp"
    }
  }
}

Example prompt: "Use Contact Finder MCP to find social profiles for openai.com and summarize the best outreach channel."

Data returned

Each tool response includes the requested contact type plus traceability fields.

Field	Type	Description
`tool`	string	Tool that was called
`domain`	string	Original domain or URL from the request
`normalizedDomain`	string	URL normalized before scanning
`emails`	array	Returned by `find_emails`
`phones`	array	Returned by `find_phones`; includes `value`, `normalized`, `format`, and `region`
`socials`	object	Returned by `find_socials`
`contactPageUrl`	string/null	Contact page found by the source crawler
`pagesCrawled`	number	Number of pages scanned by the source actor
`sourceActorRunId`	string	Internal Website Contact Finder run ID
`sourceDatasetId`	string	Internal source dataset ID
`crawledAt`	string	ISO timestamp for the tool call

How much does it cost to find contacts with MCP?

The actor uses pay-per-event pricing.

Run/session start: $0.005.
Contact tool call: $0.005 on Bronze for each find_emails, find_phones, or find_socials call, with standard tier discounts.

This price was chosen for the MCP experiment because observed source Website Contact Finder runs on small domains cost roughly $0.0001–0.0003 in Apify usage per domain, leaving room for the nested source actor run and Standby overhead while keeping agent tool calls inexpensive.

How to use it in Standby mode

Open the actor on Apify.
Use the Standby endpoint from the actor page.
Send MCP Streamable HTTP JSON-RPC requests to /mcp.
Call one of the three tools with a domain and optional max_pages.

How to use it in normal actor mode

You can also run one tool call as a regular Apify actor run.

{
  "tool": "find_emails",
  "domain": "apify.com",
  "max_pages": 5
}

The result is pushed to the default dataset.

Input

Input	Type	Default	Description
`tool`	string	`find_emails`	One of `find_emails`, `find_phones`, or `find_socials`
`domain`	string	required	Company domain or full website URL
`max_pages`	integer	`8`	Maximum internal pages to scan, from 1 to 25

Output example

{
  "tool": "find_socials",
  "domain": "apify.com",
  "normalizedDomain": "https://apify.com",
  "maxPages": 5,
  "contactPageUrl": null,
  "pagesCrawled": 5,
  "sourceActorRunId": "abc123",
  "sourceDatasetId": "def456",
  "crawledAt": "2026-05-20T00:00:00.000Z",
  "socials": {
    "linkedin": "http://linkedin.com/company/apify/",
    "twitter": "https://x.com/apify",
    "facebook": null,
    "instagram": null,
    "youtube": null,
    "github": "https://github.com/apify",
    "tiktok": "https://www.tiktok.com/@apifytech"
  }
}

MCP JSON-RPC example

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "find_emails",
    "arguments": {
      "domain": "apify.com",
      "max_pages": 5
    }
  }
}

MCP setup

The recommended MCP URL is:

https://mcp.apify.com/?tools=automation-lab/contact-finder-mcp

Example prompts:

"Find public emails for apify.com and tell me whether there is a generic sales inbox."
"Find social profiles for openai.com and draft a short SDR research note."
"Find phone numbers for this company domain and return normalized digits only."

Claude Code setup

Use the Apify MCP endpoint with the actor tool filter:

claude mcp add apify-contact-finder \
  https://mcp.apify.com/?tools=automation-lab/contact-finder-mcp

Then ask:

Find public emails for apify.com and summarize whether the domain has a general sales inbox.

Claude Desktop setup

Add an MCP server that points to Apify MCP with this actor enabled:

{
  "mcpServers": {
    "apify-contact-finder": {
      "url": "https://mcp.apify.com/?tools=automation-lab/contact-finder-mcp"
    }
  }
}

API usage with Apify client

Node.js

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('automation-lab/contact-finder-mcp').call({
  tool: 'find_socials',
  domain: 'apify.com',
  max_pages: 5,
});
console.log(run.defaultDatasetId);

Python

from apify_client import ApifyClient

client = ApifyClient('YOUR_APIFY_TOKEN')
run = client.actor('automation-lab/contact-finder-mcp').call(run_input={
    'tool': 'find_phones',
    'domain': 'apify.com',
    'max_pages': 5,
})
print(run['defaultDatasetId'])

cURL

curl -X POST "https://api.apify.com/v2/acts/automation-lab~contact-finder-mcp/runs?token=$APIFY_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{"tool":"find_emails","domain":"apify.com","max_pages":5}'

Tips for better results

Use the root domain, for example example.com, not a deep product URL.
Keep max_pages between 5 and 10 for agent workflows.
Increase max_pages only when the company hides contacts on deeper pages.
Use find_socials when a website has no obvious email; LinkedIn pages are often enough for SDR routing.

Integrations

Enrich CRM records from a domain column.
Add a contact lookup step to an outbound email drafting agent.
Check whether a target account has public social profiles before personalization.
Route leads to phone-first or email-first workflows based on returned contacts.

Architecture notes

This actor does not fork Website Contact Finder. It keeps a separate MCP interface and calls automation-lab/website-contact-finder as the internal scraping engine. That keeps the experiment isolated while preserving the production crawler boundary.

Standby and MCP mechanics

The actor enables Apify Standby mode and exposes an MCP endpoint at /mcp. It supports JSON-RPC initialize, ping, tools/list, and tools/call. Readiness probes return a simple ready response so Apify can keep the Standby container healthy.

Limitations

It finds public contact information only.
It does not log in, bypass paywalls, or access private directories.
It returns what the scanned website exposes within the selected page limit.
Some companies intentionally avoid publishing emails or phone numbers.

Legality and privacy

The actor extracts contact details publicly available on company websites. You are responsible for using the data under applicable laws such as GDPR, CAN-SPAM, and local telemarketing rules. Always respect opt-outs and avoid sending unsolicited messages where prohibited.

FAQ

Is this the same as Website Contact Finder?

No. This actor is the MCP interface. It calls Website Contact Finder internally as the scraping engine but keeps separate pricing, schemas, Standby configuration, and agent-focused tools.