mcp-company-headcount-estimator

Company Headcount Estimator MCP Server

An MCP server for the Mamba Labs Company Headcount Estimator actor on Apify. Give it a company domain or a list. Each domain returns an employee count band with the source it came from and a confidence score.

What's Inside

• What it does
• Quick start
• Prerequisites
• Example prompts
• Tool
• Inputs
• Pricing
• Your keys
• Full actor documentation
• License

What it does

For each domain the actor reads, in order: the LinkedIn company size as Google prints it in its search results (a result counts only when it shows the domain as the company website; no request goes to linkedin.com), the employee count on Wikidata for the item whose official website is the domain, and the numberOfEmployees the homepage declares. It returns employee_band, employee_band_min, employee_band_max, an exact employee_count when a source gives one, estimate_source, confidence (0 to 1), and sources_agree, plus GitHub public members and open jobs as context. Rows with no size come back free with row_status no_data.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

{
  "mcpServers": {
    "mamba-company-headcount-estimator": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-company-headcount-estimator"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}

Restart the client. The estimate_company_headcount tool appears.

Prerequisites

• Node.js 18 or newer.
• An Apify API token from console.apify.com/account/integrations, set as APIFY_TOKEN. The server lists its tool without a token; a call needs one.
• Optional: GITHUB_TOKEN, your own free GitHub token, for GitHub member counts on large batches.

Example prompts

• "How many employees does linear.app have?"
• "Estimate the headcount band for these 20 domains and keep only the ones with 51 to 500 staff."
• "Which of these companies have more than 1,000 employees, and how sure is each answer?"

Tool

estimate_company_headcount. One tool. Example arguments:

{
  "domains": ["Linear | linear.app", "posthog.com", "clay.com"]
}

Inputs

Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.

Input	Type	Description
domain	string	One company domain
company_name	string	The name for that one domain; empty reads it from the homepage
domains	array	Up to 500 domains; Name | domain.com passes the name
sources	array	Any of linkedin, wikidata, homepage, github, jobs; empty means all
skip_cache	string	true or false. Default false; a row from the last 7 days comes back free
max_charge_usd	string	Optional cost cap for the run

The actor's github_token input is filled from this server's GITHUB_TOKEN environment variable when it is set.

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

Event	Free plan	Bronze	Silver	Gold
company-estimated, per row with an employee band	$0.036	$0.0342	$0.0324	$0.0306
apify-actor-start, per run start (one per GB of run memory)	$0.0015	$0.0015	$0.0015	$0.0015

No data, invalid input, error, and cached rows are free.

Your keys

The actor needs no key. A GitHub token is optional and only raises the GitHub limit for member counts. Proxy traffic and Google result pages add nothing to your price: Mamba Labs pays the platform costs of the run.

Full actor documentation

apify.com/mambalabs/company-headcount-estimator

License

MIT. See LICENSE.