---
title: "MCP Server for Datasets and Workflows"
description: "The Tilebox MCP server gives compatible AI clients live dataset, workflow, and documentation tools."
image: "https://tilebox.com/images/tilebox-docs-social-preview.png"
---

> Documentation Index
> Fetch the complete documentation index at: https://tilebox.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server for Datasets and Workflows

import { Frame } from "@docs/components/ui/frame";
import { CardGrid } from "@docs/components/ui/card-grid";
import { LinkCard } from "@docs/components/ui/link-card";

![MCP Server](/docs/assets/changelog/2026-01-02-mcp-server.png)

The Tilebox MCP server exposes dataset and workflow tools through the Model Context Protocol. Compatible AI clients can retrieve live Tilebox information, such as a dataset's schema, instead of relying only on context pasted into a conversation. Documentation search lets agents look up how to use Tilebox before taking action.

Connect an HTTP-capable MCP client to `https://mcp.tilebox.com/mcp`. For clients that use an `mcpServers` configuration, add:

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

Authentication uses OAuth: the client opens a sign-in flow where you select a Tilebox team. No API key or custom authorization header is required. To work with multiple teams, configure separate server entries and authorize each one for its team.

    Configure HTTP transport, sign in with OAuth, and connect multiple teams.

Source: https://tilebox.com/docs/changelog/2026-01-27-mcp-server/index.mdx