# Lusha MCP

> Lusha's own MCP server and plugin: find B2B contacts and companies, enrich them with verified emails and phones, and track buying signals.

Lusha's own hosted MCP server connects your agent to Lusha's B2B contact and company data. Ask in plain words to enrich a contact, build a prospect list, check buying signals or find lookalike accounts, and get verified emails and phone numbers back. Lusha also packages it as a Claude plugin and a Gemini CLI extension, with skills for prospecting and outreach.

What you can do with it
- Enrich a person from an email, a LinkedIn URL or a name and company, with their verified work email and direct and mobile phone numbers
- Search for contacts by job title, seniority, location and department, and for companies by firmographic and technographic filters
- Find the buying committee and the decision makers at a target account
- Find contacts and companies that look like your best customers
- Search buying signals such as job changes, promotions, funding, hiring surges and headcount growth, and see which companies visit your website
- Build workspace tables, add enrichment or AI columns and run them over every row
- Push enriched contacts and companies into Salesforce, HubSpot, Zoho, Pipedrive or SalesLoft
- Search call recordings and pull their transcripts
- Check your credit balance and rate limits

Its plugin skills
The Claude plugin and the Gemini CLI extension add six skills on top of the server. enrich-contact, prospect, signal-prospect and lookalike-prospect find and enrich people, with phone numbers first. outreach-research captures what you sell as a reusable brief, and outreach-sequence drafts short, signal-based emails and LinkedIn messages from it.

How it connects
- Lusha hosts it at https://mcp.lusha.com/mcp.
- In Claude, ChatGPT and Codex you sign in to your Lusha account with OAuth the first time. The Claude plugin and the Gemini CLI extension sign in with OAuth too.
- For other clients, such as Cursor, VS Code and n8n, Lusha's docs connect with your Lusha API key in an x-api-key header.

Good to know
- It needs a Lusha plan that includes API access, and it uses the same credits as Lusha's API. Searches and lookups generally charge only for matched results; filter lookups and account checks are free.
- The recommendations tools only work over an OAuth connection.
- Only account admins can connect a CRM.

- Type: Plugin
- Made by: Lusha
- Category: Sales
- Formats: Remote MCP, Claude plugins, Extensions
- Version: latest
- Website: https://docs.lusha.com/mcp/overview
- Source: https://github.com/lusha-oss/lusha-mcp-plugin
- Page: https://pluginboard.ai/plugins/lusha-mcp

## Works with

- ChatGPT
- Claude
- Muse
- Grok Bot
- Gemini
- Grok
- GitHub Copilot
- Cursor
- Claude Code
- Codex
- Antigravity
- Gemini CLI
- Replit
- OpenClaw
- OpenCode
- Hermes Agent

## Install

### ChatGPT

In ChatGPT on the web: Plugins → + → Add custom MCP server, then paste https://mcp.lusha.com/mcp under Connection. Business and Enterprise plans; Pro can add read-only servers.

### Claude

In Claude (web or desktop): Customize → Plugins → Add → Add marketplace, enter anthropics/knowledge-work-plugins, then add lusha

### Muse

In Muse: In a Muse chat, ask it to create a custom connector for the MCP server at https://mcp.lusha.com/mcp. Then tap Connect on the card it shows and sign in, or add your key.

### Grok Bot

In Grok Bot: In a chat with your Bot, say "Add this MCP server: https://mcp.lusha.com/mcp". It confirms the details with you and sets it up, and the tools are ready from your next message.

### Gemini

In Gemini: At gemini.google.com: Settings → Connected Apps → Add a custom app, then paste https://mcp.lusha.com/mcp

### Grok

In Grok on the web: At grok.com/connectors: New Connector → Custom, then enter https://mcp.lusha.com/mcp and sign in if it asks.

### GitHub Copilot

Add to VS Code: vscode:mcp/install?%7B%22name%22%3A%22lusha-mcp%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.lusha.com%2Fmcp%22%7D

Copilot CLI:

```shell
copilot mcp add --transport http lusha-mcp https://mcp.lusha.com/mcp
```

### Cursor

Add to Cursor: cursor://anysphere.cursor-deeplink/mcp/install?name=lusha-mcp&config=eyJ1cmwiOiJodHRwczovL21jcC5sdXNoYS5jb20vbWNwIn0%3D

Add to .cursor/mcp.json:

```json
{
  "mcpServers": {
    "lusha-mcp": {
      "url": "https://mcp.lusha.com/mcp"
    }
  }
}
```

### Claude Code

In Claude Code:

```text
/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install lusha@knowledge-work-plugins
```

### Codex

Run in your terminal:

```shell
codex mcp add lusha-mcp --url https://mcp.lusha.com/mcp
```

### Antigravity

Add to ~/.gemini/config/mcp_config.json:

```json
{
  "mcpServers": {
    "lusha-mcp": {
      "url": "https://mcp.lusha.com/mcp"
    }
  }
}
```

### Gemini CLI

Run in your terminal:

```shell
gemini extensions install https://github.com/lusha-oss/lusha-mcp-plugin
```

### Replit

In Replit: At replit.com/integrations, open MCP Servers → + Add MCP server, paste https://mcp.lusha.com/mcp (add any headers under Advanced settings), then click Test & save.

### OpenClaw

Run in your terminal:

```shell
openclaw mcp add lusha-mcp --url https://mcp.lusha.com/mcp --transport streamable-http
```

If it needs a key or sign-in: For https://mcp.lusha.com/mcp, add --header NAME=value for each header it needs, or --auth oauth and then run openclaw mcp login lusha-mcp.

### OpenCode

Run in your terminal:

```shell
opencode mcp add lusha-mcp --url https://mcp.lusha.com/mcp
```

If it needs a key: For https://mcp.lusha.com/mcp, add --header 'NAME=value' for each header it needs. Add --global to use it in every project.

### Hermes Agent

Run in your terminal:

```shell
hermes mcp add lusha-mcp --url https://mcp.lusha.com/mcp
```

Add to ~/.hermes/config.yaml:

```json
{
  "mcp_servers": {
    "lusha-mcp": {
      "url": "https://mcp.lusha.com/mcp"
    }
  }
}
```

If it signs in with OAuth: If https://mcp.lusha.com/mcp asks you to sign in, add --auth oauth to the command, or auth: oauth to its entry.

---
From Pluginboard (https://pluginboard.ai).