> For the complete documentation index, see [llms.txt](https://help.leadboxer.com/leadboxer/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.leadboxer.com/leadboxer/platform-and-api/mcp-server.md).

# MCP Server for AI Assistants

The LeadBoxer MCP server lets AI assistants such as Claude, Claude Code and Cursor look up companies and contacts with your LeadBoxer account. Ask "Who is behind IP 193.8.9.0?", "Enrich acme.com" or "Who is <jane.doe@acme.com>?" and the assistant calls LeadBoxer for you.

| Tool                 | What it does                                                                                                       | Credits                                       |
| -------------------- | ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------- |
| `lookup_ip`          | Identifies the company behind an IP address: organisation, domain, ISP, usage type and location                    | 20                                            |
| `lookup_domain`      | Enriches a company domain with firmographics: industry, employees, description, address and LinkedIn               | 10                                            |
| `lookup_email`       | Finds the professional profile behind a work email: name, headline, LinkedIn, seniority, location and work history | 50 per profile found, none if no one is found |
| `get_credit_balance` | Shows your remaining credits                                                                                       | Free                                          |

All tools are read-only: they never change data in your LeadBoxer account. Lookups use the same credits as the App.

### Connect it

You need your LeadBoxer API key, from [Integrations → Data → API key](https://app.leadboxer.com/integrations-connectors/data/api-key) in the App. The server address and step-by-step setup for Claude, Claude Code, ChatGPT, Cursor, VS Code and other clients are on the developer portal: [LeadBoxer MCP server](https://developers.leadboxer.com/docs/mcp).

Read more about what you can do with it on [leadboxer.com/mcp](https://www.leadboxer.com/mcp).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.leadboxer.com/leadboxer/platform-and-api/mcp-server.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.