Skip to main content
Glama
ExtractorLead MCP Server

ExtractorLead MCP Server

ExtractorLead for Claude (MCP + Skill)

Find B2B/B2C leads (emails and phone numbers) on LinkedIn, Instagram, TikTok and websites, and enrich your own contact lists, directly from Claude.

  • MCP server — 13 tools that call the ExtractorLead API with your account (sign in with OAuth, or use an API key).

  • Skill — teaches Claude the workflow: check balance, quote, ask before spending credits, poll async jobs, deliver results.

Every action is billed to your ExtractorLead account, exactly as through the API. Claude always asks for confirmation before launching anything that costs credits.

1. Add it to Claude

claude.ai and Claude Desktop (custom connector)

  1. Customize → Connectors → Add custom connector (Team/Enterprise: an Owner adds it under Organization settings → Connectors).

  2. Name: ExtractorLead · URL: https://api.extractorlead.com/mcp → Add. Leave the advanced settings empty.

  3. Click Connect, sign in to ExtractorLead (or create a free account) and click Allow. No API key needed.

  4. Enable it in a chat from the + → Connectors menu.

Disconnect it any time from https://app.extractorlead.com/profile → API & Claude.

Skill (recommended): download extractorlead-skill.zip and upload it at Customize → Skills → + → Upload a skill.

Claude Code (plugin: connector + skill in one step)

/plugin marketplace add NeuroBlockFoundation/extractorlead-mcp
/plugin install extractorlead@extractorlead

Then run /mcp, pick extractorlead → Authenticate and sign in to ExtractorLead in the browser.

Connector only, without the skill:

claude mcp add --transport http extractorlead https://api.extractorlead.com/mcp

Prefer an API key (CI, scripts)? Create one at https://app.extractorlead.com → Profile → API keys and add --header "X-API-Key: sk_live_...".

Local server (stdio)

Useful for passing a CSV/XLSX straight from disk (file_path), which the remote connector can't read. It uses an API key from Profile → API keys.

{
  "mcpServers": {
    "extractorlead": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/NeuroBlockFoundation/extractorlead-mcp", "extractorlead-mcp"],
      "env": { "EXTRACTORLEAD_API_KEY": "sk_live_..." }
    }
  }
}

Claude Desktop: %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).

Related MCP server: Prospeo MCP Server

2. Try it

Find me 25 emails of marketing directors at SaaS companies in Madrid.

Here's my Sales Navigator export: get me phones and emails, quote first.

Fill the missing phones in this CRM list and give me back the Excel.

Tools

Tool

Costs credits

What it does

get_account

no

Balance and plan

search_leads

yes

New leads by niche + location (LinkedIn / Instagram / TikTok, emails or phones)

lookup_linkedin_profile

yes

Contact details for one LinkedIn profile

analyze_website

yes

Contacts and business info from a website

get_task_result

no

Status/result of the three above (waits up to 50 s, paginated)

preview_bulk_enrichment

no

Validate + quote a list of people

start_bulk_enrichment

yes

Enrich up to 5,000 people (email 2, phone 3, both 4 credits per delivered contact)

get_bulk_status / get_bulk_results / get_bulk_download_link

no

Track and fetch a bulk job

preview_list_enrichment

no

Analyze your own list and quote filling its gaps

start_list_enrichment

up to credit_cap

Fill gaps; returns your same Excel with new columns

get_list_enrichment

no

Status + download link of the edited Excel

Phones in bulk jobs arrive asynchronously (up to ~1 hour, phase: awaiting_phones). Claude tells you and you can ask again later with the same job.

Development

pip install -e ".[test]" pytest-asyncio
pytest
extractorlead-mcp            # stdio (needs EXTRACTORLEAD_API_KEY)
extractorlead-mcp --http     # remote multi-user server on :8080, /mcp + /health
python scripts/build_skill_zip.py   # dist/extractorlead-skill.zip
claude plugin validate .

EXTRACTORLEAD_API_URL overrides the API base URL (default https://api.extractorlead.com; in the cluster it points to the internal Service). In HTTP mode the server never uses a key from its environment or reads its own disk: every request must bring the user's credential, and /mcp answers 401 with WWW-Authenticate: Bearer resource_metadata=... when it doesn't, which is what makes Claude offer Connect.

  • OAuth 2.1 (default): api.extractorlead.com is the authorization server (/.well-known/oauth-authorization-server, Dynamic Client Registration at /oauth/register, PKCE S256, rotating refresh tokens). Claude sends Authorization: Bearer elo_at_...; the gate checks it against the API and answers 401 invalid_token when it expired so Claude refreshes it.

  • API key: X-API-Key, Authorization: Bearer sk_live_..., or ?api_key= (legacy). The access log is disabled so keys in the URL aren't written to logs.

Deployment: the remote server runs on ExtractorLead's infrastructure (image from Dockerfile, Terraform stack extractor-lead/mcp). This public repository is a mirror synced automatically on every release.

Available Tools

13 tools
analyze_websiteAnalizar webA

Analiza una web: contactos (emails, teléfonos, redes), negocio y servicios.

url debe incluir http:// o https://. Devuelve un task_id para get_task_result.

Inputs: url (required), language. Returns: object

get_accountSaldo y planA
Read-only

Saldo de créditos y estado de la suscripción de ExtractorLead.

Úsalo antes de lanzar cualquier trabajo para saber si hay saldo suficiente.

Inputs: no named parameters. Returns: object

get_bulk_resultsLeads del enriquecimiento masivoB
Read-only

Leads enriquecidos de un trabajo masivo, paginados (per_page máx. 200).

Para listas grandes ofrece al usuario get_bulk_download_link en vez de paginar todo en la conversación.

Inputs: task_id (required), only, page, match, +1 more. Returns: object

get_bulk_statusEstado del enriquecimiento masivoA
Read-only

Contadores de un trabajo masivo (nunca la lista).

phase: processing | awaiting_phones | completed. Con partial=true ya se pueden leer los leads decididos con get_bulk_results. Los teléfonos pueden tardar hasta ~1 hora: si phase es awaiting_phones, avisa al usuario y vuelve a consultar más tarde en lugar de esperar en bucle.

Inputs: task_id (required), wait_seconds. Returns: object

get_list_enrichmentEstado del relleno de listaB
Read-only

Estado del relleno de lista; al terminar, resumen y enlace al Excel editado.

include_rows=true añade las filas (paginadas con offset/limit, máx. 200).

Inputs: task_id (required), limit, offset, include_rows, +1 more. Returns: object

get_task_resultResultado de una búsquedaA
Read-only

Estado y resultado de search_leads, lookup_linkedin_profile o analyze_website.

  • wait_seconds: espera hasta 50s a que termine antes de responder.

  • offset/limit: paginación de la lista de leads cuando es larga. status: PENDING | PROCESSING | COMPLETED | FAILED | CANCELLED.

Inputs: task_id (required), limit, offset, wait_seconds. Returns: object

lookup_linkedin_profileEnriquecer perfil de LinkedInA

Obtiene email, teléfono y datos profesionales de UN perfil de LinkedIn.

linkedin_url: https://www.linkedin.com/in// Devuelve un task_id; el resultado se recoge con get_task_result.

Inputs: linkedin_url (required). Returns: object

preview_bulk_enrichmentCotizar enriquecimiento masivoA
Read-only

Valida una lista de personas y calcula el coste máximo. NO cobra nada.

Úsalo SIEMPRE antes de start_bulk_enrichment y enseña al usuario
rows_accepted, max_credits y available_credits.

Entrada (una de las dos):
- leads: lista de filas, cada una con los campos que tenga: first_name,
  last_name, full_name, company, domain, title, linkedin_url, email,
  location. También valen cabeceras en español (Nombre, Apellido, Cargo,
  Empresa, LinkedIn...). Máx. 5000 filas.
- file_path: ruta a un CSV/XLSX local (solo servidor local; un export de
  Sales Navigator vale tal cual).
Opciones:
- contact_info: "all_contact_info" (por defecto: pide el teléfono y entrega
  el email solo de quien tiene teléfono), "phone_info" o "email_info".
- match_mode: "strict" (la persona exacta) o "related" (además otros
  contactos análogos de la misma empresa, usando el cargo como semilla).
- related_per_company: 1..10 contactos análogos por empresa (con related).
- require_mobile: true para contar solo móviles, no centralitas.
Precio por contacto ENTREGADO: solo email 2, solo teléfono 3, ambos 4,
nada 0 créditos.

Inputs: leads, file_path, match_mode, contact_info, +2 more. Returns: object

preview_list_enrichmentCotizar relleno de listaA
Read-only

Analiza una lista propia (CRM, Excel) y cotiza rellenar sus huecos. NO cobra.

A diferencia del enriquecimiento masivo, conserva las columnas del usuario y devuelve su mismo Excel con columnas nuevas. Devuelve columnas detectadas, huecos (sin_telefono, sin_email...), coste y tope_sugerido.

  • phone_for_all: true para buscar teléfono también en filas que ya traen uno (p.ej. cuando son centralitas).

Inputs: leads, file_path, wants_phone, phone_for_all. Returns: object

search_leadsBuscar leads por nichoA

Busca leads nuevos de un nicho en una zona. Consume créditos.

  • channel: "linkedin" para B2B (cargos, empresas), "instagram"/"tiktok" para creadores y negocios locales.

  • contact: "emails" o "phones".

  • niche: a quién buscas, p.ej. "directores de marketing de SaaS" o "clínicas dentales".

  • location: ciudad, región o país, p.ej. "Madrid".

  • lead_count: 1..500 (por defecto 25).

  • country: código ISO de 2 letras, solo para linkedin+phones (p.ej. "es").

Devuelve un task_id; recoge los leads con get_task_result. Pide confirmación al usuario antes de llamarla.

Inputs: niche (required), channel (required), contact (required), location (required), +2 more. Returns: object

start_bulk_enrichmentLanzar enriquecimiento masivoA

Lanza el enriquecimiento de una lista de personas. Consume créditos.

Solo tras preview_bulk_enrichment y con la confirmación del usuario.
Devuelve un task_id; sigue el trabajo con get_bulk_status.

Entrada (una de las dos):
- leads: lista de filas, cada una con los campos que tenga: first_name,
  last_name, full_name, company, domain, title, linkedin_url, email,
  location. También valen cabeceras en español (Nombre, Apellido, Cargo,
  Empresa, LinkedIn...). Máx. 5000 filas.
- file_path: ruta a un CSV/XLSX local (solo servidor local; un export de
  Sales Navigator vale tal cual).
Opciones:
- contact_info: "all_contact_info" (por defecto: pide el teléfono y entrega
  el email solo de quien tiene teléfono), "phone_info" o "email_info".
- match_mode: "strict" (la persona exacta) o "related" (además otros
  contactos análogos de la misma empresa, usando el cargo como semilla).
- related_per_company: 1..10 contactos análogos por empresa (con related).
- require_mobile: true para contar solo móviles, no centralitas.
Precio por contacto ENTREGADO: solo email 2, solo teléfono 3, ambos 4,
nada 0 créditos.

Inputs: leads, file_path, match_mode, contact_info, +2 more. Returns: object

start_list_enrichmentLanzar relleno de listaB

Lanza el relleno de huecos de una lista. Consume créditos hasta credit_cap.

credit_cap: tope de gasto que el usuario ha aprobado (usa el tope_sugerido de preview_list_enrichment si no dice otro). Sigue el trabajo con get_list_enrichment.

Inputs: credit_cap (required), leads, file_path, wants_phone, +1 more. Returns: object

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 13 tools

    Disambiguation3/5

    Most tools are clearly distinct (account, search, single-profile lookup, website analysis), but the surface contains two parallel pipelines that are easy to conflate: preview_bulk_enrichment/start_bulk_enrichment/get_bulk_status/get_bulk_results versus preview_list_enrichment/start_list_enrichment/get_list_enrichment. The descriptions do explain the difference (bulk = discover contacts from a person list, list = fill gaps preserving user columns), but an agent must read carefully to pick correctly. Polling is also split across three different mechanisms (get_task_result, get_bulk_status/results, get_list_enrichment), which adds a second layer of selection risk.

    Naming Consistency5/5

    Every tool follows a consistent snake_case verb_noun pattern (get_account, search_leads, preview_bulk_enrichment, start_bulk_enrichment, get_bulk_results, get_list_enrichment). The bulk/list prefixes create a predictable family structure, and the preview_/start_/get_ prefixes signal lifecycle stage clearly.

    Tool Count5/5

    13 tools is well within the well-scoped 3-15 range. Each tool maps to a real step of the two enrichment workflows plus the lead-search workflow, and none appear redundant at the surface level.

    Completeness4/5

    Coverage is strong: credits/account, lead search, single-profile lookup, website analysis, task polling, and full preview/start/status/results/download lifecycles for both bulk and list enrichment. Minor gaps remain — there is no cancellation tool despite a CANCELLED status being exposed, and no task/job history listing, though agents can work around both.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Give your AI agent access to 60M+ companies and 300M+ verified contacts. Enrich leads, find work emails, discover tech stacks, and identify buying intent — directly from Claude, Cursor, Windsurf, or any MCP-compatible AI agent.
      11
      9 npm
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI tools to search and enrich B2B leads, including finding professional emails, company profiles, and filtering people and companies by various criteria.
      5
      429 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables B2B prospecting from natural language: detect buying signals, score leads against ICP, enrich decision-makers, and draft personalized outreach messages via Claude.
      3
      MIT