Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 39 additions & 26 deletions ai-assistance.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -4,49 +4,62 @@ description: Large Language Models (LLMs) are powerful tools for exploring and l
icon: brain-circuit
---

## Providing complete Tilebox context
## Tilebox MCP Server

AI assistants and Large Language Models (LLMs) can answer questions, guide you in using Tilebox, suggest relevant sections in the documentation, and assist you in creating workflows.
The Model Context Protocol (MCP) is an open protocol that creates standardized connections between AI applications and
external services. Tilebox provides such an MCP server that exposes tools for listing, querying and retrieving the schema
of datasets, as well as tools for interacting with workflows.

<Card title="Download documentation for LLMs" icon="brain-circuit" href="https://docs.tilebox.com/llms-full.txt" horizontal>
Download the complete Tilebox documentation as a plain text file to share with your AI assistant or language model.
</Card>

The full content of the Tilebox documentation is available in plain markdown format at [https://docs.tilebox.com/llms-full.txt](https://docs.tilebox.com/llms-full.txt). Upload this document to your AI assistant or LLM to provide it with Tilebox-specific context.

<Tip>
The [Documentation Context](https://docs.tilebox.com/llms-full.txt) is updated whenever the documentation changes. If you download the file, refresh it occasionally to stay up-to-date.
</Tip>

## Providing tailored context via MCP
### How the Tilebox MCP servers can help

Tilebox Docs can be installed as an MCP tool, so an MCP client can ask for detailed context on specific topics.

### For Claude Desktop
When an AI tool like Claude, Cursor, or ChatGPT has the Tilebox MCP server configured, it can proactively invoke relevant
tools. For example, when asking a question about a specific dataset, the AI tool can query the Tilebox MCP server for the
dataset schema and include the correct, and up-to-date information about it in the response.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would mention that together they let the LLM or coding assistant know how it can write code for Tilebox (using the docs), and then also specifically let the LLM customize that code depending on what custom datasets are available, or let the LLM take action (more capabilities coming).

Run the following command to add Tilebox Docs to Claude:
Tilebox provides two MCP servers:

```bash
claude mcp add --transport http "Tilebox Docs" https://docs.tilebox.com/mcp
```
- `https://mcp.tilebox.com/` - This MCP server provides tools for accessing and interacting with Tilebox datasets and workflows. It requires authentication using a Tilebox API key.
- `https://docs.tilebox.com/mcp` - This MCP server provides access to the Tilebox documentation. It does not require authentication. When configured, AI agents can ask for detailed context on specific topics.

### For other MCP clients
### Configuring the Tilebox MCP servers

1. Open command palette (Cmd+Shift+P / Ctrl+Shift+P)
2. Search "Open MCP settings"
3. Select "Add custom MCP"
4. Add to mcp.json:
To configure your AI tools to use the Tilebox MCP servers, you need to point it to the correct URLs using the `http` transport.
Additionally you'll need to provide an `Authorization` header with your Tilebox API key as the bearer token for the `https://mcp.tilebox.com/` server.

```json
{
"mcpServers": {
"tilebox": {
"url": "https://mcp.tilebox.com/",
"headers": {
"Authorization": "Bearer <YOUR_TILEBOX_API_KEY>"
}
},
"tilebox-docs": {
"url": "https://docs.tilebox.com/mcp"
}
}
}
```

### For Claude Desktop

Run the following commands to add the Tilebox MCP server to Claude:

```bash
claude mcp add --transport http "Tilebox" https://mcp.tilebox.com/ --header "Authorization: Bearer <YOUR_TILEBOX_API_KEY>"
claude mcp add --transport http "Tilebox Docs" https://docs.tilebox.com/mcp
```

## Providing the full Tilebox documentation as context

<Card title="Download documentation for LLMs" icon="brain-circuit" href="https://docs.tilebox.com/llms-full.txt" horizontal>
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess we can mention that this does not contain dynamic content, and only "replaces" the docs mcp server

Download the complete Tilebox documentation as a plain text file to share with your AI assistant or language model.
</Card>

The full content of the Tilebox documentation is available in plain markdown format at [https://docs.tilebox.com/llms-full.txt](https://docs.tilebox.com/llms-full.txt). Upload this document to your AI assistant or LLM to provide it with Tilebox-specific context.

<Tip>
The MCP server always retrieves the most up to date version of the documentation.
The [Documentation Context](https://docs.tilebox.com/llms-full.txt) is updated whenever the documentation changes. If you download the file, refresh it occasionally to stay up-to-date.
</Tip>