Skip to main content
Glama

🎯 MCP Hunter

MCP Server (Model Context Protocol) for OSINT, Active Prospecting, Web Search, Deep Scraping, and Data Enrichment of Companies and People.

MCP Hunter connects AI assistants (such as Gemini Antigravity, Claude Desktop, Cursor, and Windsurf) directly to the internet and open data sources. It can search Google/Web, intelligently scrape and clean pages, extract contacts (emails, WhatsApp, phone numbers, social media), and enrich company profiles with official Receita Federal data (CNPJ, Partners/QSA, Share Capital, and Address).


✨ Main Features

  • 🔍 Web Search Without Paid Keys: Fast search with support for advanced operators (site:, inurl:, filetype:) and regional focus on Brazil (br-pt).

  • 🌐 Smart Content Scraping and Cleaning: Uses trafilatura and BeautifulSoup to extract only the main text, removing ads, menus, and code.

  • 📞 Surgical Contact Extractor: Regex algorithms and heuristics to identify:

    • Valid emails (with anti-spam and anti-image filtering);

    • Landline and mobile numbers in the Brazilian format;

    • Direct WhatsApp links (wa.me/ and api.whatsapp.com);

    • Official social media profiles (Instagram, LinkedIn, Facebook, X/Twitter, YouTube, TikTok, GitHub);

    • CNPJ numbers with mathematical validation of check digits.

  • 🏛️ Official Receita Federal Query (BrasilAPI): Retrieves Legal Name, Trade Name, Registration Status, Opening Date, Share Capital, Primary Activity (CNAE), Address, and Board of Partners and Administrators (QSA).

  • 🏢 Master Mode (hunt_company): Takes a company name and runs the end-to-end 360º investigation in seconds.

  • 👤 People Investigation (hunt_person): Scans public mentions, LinkedIn profiles, and articles about a person.


Related MCP server: LeadSpark MCP

🛠️ Exposed Tools

Tool

Description

Main Parameters

hunter_search

Searches the Web/Google, returning links, titles, and summarized snippets.

query (str), max_results (int, default: 5), region (str, default: 'br-pt')

scrape_website

Visits the site, extracts readable text, and scans contact subpages (/contato, /sobre, /termos).

url (str), deep_contacts (bool, default: true)

extract_contacts

Analyzes a URL or raw text and extracts emails, phone numbers, WhatsApp, social media, and CNPJ.

url (str, optional), text (str, optional)

consult_cnpj

Queries the Receita Federal database via BrasilAPI / MinhaReceita.

cnpj (str)

hunt_company

Company 360º Dossier: searches the website, extracts contacts, social media, CNPJ, and corporate structure.

company_name (str), domain_or_url (str, optional)

hunt_person

Investigates public presence, LinkedIn profiles, and web mentions about a person.

name (str), context (str, optional)


🚀 Installation and Execution

This project uses the ultra-fast package manager uv.

1. Clone the repository

git clone <URL_DO_REPOSITORIO>
cd "MCP Hunter"

2. Install dependencies automatically

uv sync

3. Run the automated tests

uv run python tests/test_tools.py

4. Start the MCP server (stdio mode)

uv run mcp-hunter

🔌 Configuration in MCP Clients

Antigravity / Claude Desktop / Cursor / Windsurf

Add the configuration below to your MCP configuration file (claude_desktop_config.json or similar):

{
  "mcpServers": {
    "mcp-hunter": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\caminho\\para\\MCP Hunter",
        "run",
        "mcp-hunter"
      ]
    }
  }
}

📂 Project Structure

MCP Hunter/
├── src/
│   └── mcp_hunter/
│       ├── __init__.py        # Definição do pacote
│       ├── server.py          # Servidor FastMCP e registro das Tools
│       ├── search.py          # Motor de buscas na Web (DuckDuckGo/DDGS)
│       ├── scraper.py         # Motor de requisições HTTP e scraping (Trafilatura/BS4)
│       ├── extractor.py       # Extração de contatos, regex e validação de CNPJ
│       ├── cnpj.py            # Integração com BrasilAPI e Receita Federal
│       └── py.typed           # Marcador de tipagem PEP 561
├── tests/
│   ├── test_hunter.py         # Testes unitários dos módulos internos
│   └── test_tools.py          # Testes de integração das ferramentas MCP
├── mcp_config_example.json    # Exemplo de configuração de cliente MCP
├── pyproject.toml             # Configuração do projeto e dependências
├── uv.lock                    # Lockfile de dependências
└── README.md                  # Documentação oficial

📄 License

Distributed under the MIT license. See LICENSE for more information.

Available Tools

6 tools
consult_cnpjA

Consulta dados oficiais de uma empresa brasileira na Receita Federal (BrasilAPI).

Args: cnpj: Número do CNPJ com ou sem pontuação (ex: 00.000.000/0001-91 ou 00000000000191).

Returns: Dossiê cadastral oficial com Razão Social, Sócios (QSA), Capital Social, Endereço e Contatos.

Inputs: cnpj (required). Returns: result

extract_contactsA

Extrai cirurgicamente e-mails, telefones, WhatsApp, redes sociais e CNPJs de uma URL ou texto.

Args: url: URL do site a ser vasculhado (opcional se 'text' for fornecido). text: Texto bruto para análise de entidades (opcional se 'url' for fornecida).

Returns: Relatório estruturado com todos os contatos identificados.

Inputs: url, text. Returns: result

hunt_companyA

Dossiê 360º de Empresa: busca site oficial, extrai contatos, redes sociais, CNPJ e sócios.

Args: company_name: Nome da empresa ou marca. domain_or_url: Site oficial da empresa (se já souber, agiliza a busca).

Returns: Dossiê de inteligência completo sobre a empresa.

Inputs: company_name (required), domain_or_url. Returns: result

hunt_personA

Investiga a presença pública de uma pessoa (LinkedIn, cargos, menções e notícias).

Args: name: Nome completo da pessoa. context: Contexto adicional (empresa onde trabalha, cidade, cargo, etc.).

Returns: Resumo de perfis e menções públicas encontradas.

Inputs: name (required), context. Returns: result

scrape_websiteA

Acessa um site, remove lixo/anúncios e extrai o texto legível e subpáginas de contato.

Args: url: URL completa do site (ex: https://empresa.com.br). deep_contacts: Se True, vasculha também páginas internas como /contato e /sobre.

Returns: Texto limpo e estruturado extraído da página.

Inputs: url (required), deep_contacts. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 6 tools

    Disambiguation3/5

    Most tools have distinct purposes, but scrape_website, extract_contacts, and hunt_company overlap when the goal is finding contact information from a URL. The descriptions help clarify scope, but an agent could still be uncertain whether to scrape, extract, or run a full company dossier.

    Naming Consistency4/5

    Five of six tools follow a consistent verb_noun pattern in snake_case (scrape_website, extract_contacts, hunt_company, hunt_person, consult_cnpj). hunter_search breaks the pattern by using the agent-noun 'hunter' instead of the verb 'hunt'.

    Tool Count5/5

    Six tools is well-scoped for an OSINT/company-research server. It covers search, scraping, contact extraction, company/person investigation, and official CNPJ lookup without unnecessary bloat or feeling too thin.

    Completeness4/5

    The set covers the core intelligence workflow: search, scrape, extract contacts, investigate companies/people, and consult official records. Minor gaps exist, such as no explicit reverse-lookup or export/verification tool, but the main workflows do not hit dead ends.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables Brazilian business data lookup through CNPJ (company registry) and CEP (postal code) queries, with intelligent web search capabilities powered by Tavily for due diligence, compliance, and customer verification.
      84 npm
      10
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to research companies and find contacts with structured data from multiple free sources, including company info, tech stack, and email addresses.
      3
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Brazilian company-registry lookup via Receita Federal, allowing AI agents to query CNPJ data.
      100 npm
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables lookup of Brazilian public data including companies (CNPJ), postal codes (CEP), banking, economy, geography, and more through 15 tools and 2 guided prompts, powered by BrasilAPI with no API key required.
      15
      MIT