Skip to main content
Audience: Admins and developers setting up the Lusha MCP Server for the first time, or evaluating what the integration can do at a technical level. If you’re already connected and want to know how to use Lusha inside Claude, ChatGPT, or Codex, see Using Lusha inside LLMs.
The Lusha MCP Server is a Model Context Protocol server that exposes Lusha’s B2B contact and company data as callable tools. MCP-compatible AI clients - including Claude, ChatGPT, Codex, Cursor, and VS Code - can invoke those tools through natural language, without any custom API integration. Lusha is also listed on Gong Collective, so Gong customers can connect the same MCP tools straight into Gong’s AI Briefer.

​
What you can do

  • Search for contacts and companies by name, title, industry, location, and more
  • Enrich contact profiles with verified emails and phone numbers
  • Build targeted prospect tables inside your AI chat
  • Run full prospecting workflows - from ICP to outreach - in a single conversation
  • Pull AI-driven Recommendations - contacts and companies tailored to your ICP - directly inside your AI conversation
  • Rank any contact or company list on a 0-100 buying-signal scale with Signal Score, using the signal_score_contacts and signal_score_companies tools - see Signal Score and ICP Fit Score for how scores are calculated
  • Score how likely a company is to become a sales opportunity with Opportunity Conversion Score (Beta), using the predictive_score_companies tool, and get the reasons behind the score - see Opportunity Conversion Score (Beta) explained for what the score means and which CRMs are supported
  • Find Lookalikes of your best customers and pipe them straight into Enrich for full contact details
  • Query Website Visitors data to see which companies are browsing your site and act on them directly inside your AI conversation
  • Search your account’s recorded sales calls with Conversation Intelligence - by date, company, participant, or keyword - then pull a call’s summary, coaching scores, chapters, or transcript, using the conversations_search and conversations_transcript_get tools; see Conversation Intelligence API for credit costs and what’s included
In Claude, contacts and companies render as interactive cards instead of plain text - with one-click copy and one-click signal pulls (buying signals, hiring, headcount shifts, website traffic, LinkedIn activity intent, and more). If you run out of credits mid-search, you can top up right from the card without leaving the conversation.

​
Requirements

  • A Lusha account on any plan - every user can connect their own Lusha MCP Server, subject to your account’s MCP access permission. Admins can restrict MCP access separately: a dedicated MCP access permission in Account Settings → Permissions is on by default - turn it off and only Admins and Managers can connect.
  • Available API credits - MCP calls consume credits from your account’s credit pool
  • An MCP-compatible AI client. Lusha supports two connection methods, depending on your client:
    • OAuth - one-click authentication via Lusha’s official connector, for Claude, ChatGPT, and Codex. Not gated by Admin/Manager role or by your account’s API key permission settings.
    • API Key - pass your Lusha API key via the x-api-key request header, for VS Code, Cursor, n8n, Gemini CLI, Gong AI Briefer, and any other MCP-compatible client. Subject to your account’s API key permission settings.
MCP Server URL (for API Key clients): https://mcp.lusha.com. Get your API key from API Hub → Manage API Keys.
Starter prompt included: Every Lusha MCP connection now ships with a ready-to-use starter prompt right on the consent screen - copy it in one click to try a real example (find a person, verify they still work there, and pull their title and verified contact details) the moment you connect. This ships across every MCP client we connect to, not just Claude.

​
Connect Lusha now

Connect via Claude - click Add to Claude and complete OAuth authentication. Connect via ChatGPT - find Lusha in the app directory and click Connect. Connect via Codex - find Lusha in the Codex plugin directory and click Connect. Connect via Gong - in Gong, go to Settings → MCP connections, select Lusha, authenticate, and enable the tools you want for AI Briefer.

​
Full setup guide and documentation

For complete setup instructions, available tool schemas, example prompts, troubleshooting, and security guidance, visit the full MCP documentation on the Lusha developer portal:
👉 MCP Server documentation on docs.lusha.com
(a) Data brokers and other third-party platforms may not embed, expose, or otherwise provide access to the Lusha API, or to Data obtained through it, on or through their own website, product, or service, without Lusha’s prior written consent. (b) Data obtained through the API may not be used to train or develop AI/ML systems, subject to the terms and exceptions outlined in the Terms and Conditions.