> For the complete documentation index, see [llms.txt](https://ottodata.gitbook.io/ottodata-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ottodata.gitbook.io/ottodata-docs/mcp-for-ai-agents/install-in-your-client.md).

# Install in your client

## Install in your client

The server URL for every client:

```
https://api.ottodata.app/mcp
```

### Cursor

One-click: use the install deeplink in the [otto-data README](https://github.com/Degergokalp/otto-data#mcp-server), or add manually to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (per project):

```json
{
  "mcpServers": {
    "otto-data": { "url": "https://api.ottodata.app/mcp" }
  }
}
```

Then check Cursor Settings → MCP — you should see 17 tools listed.

### Claude Code

```bash
claude mcp add --transport http otto-data https://api.ottodata.app/mcp
```

### Claude.ai / Claude Desktop (custom connector)

Settings → Connectors → **Add custom connector** → paste the URL above. No login is required since the server is authless.

Claude Desktop also supports local stdio mode if you prefer running the server yourself:

```json
{
  "mcpServers": {
    "otto-data": {
      "command": "python3",
      "args": ["/path/to/otto-data/mcp_server/server.py"]
    }
  }
}
```

(The stdio server talks to the live REST API; set `OTTO_API_URL` to override.)

### Any other MCP client

Any client that supports **streamable HTTP** transport works — just point it at the endpoint. No headers, tokens or session setup needed.

### Verify it works

Ask your agent something only Otto can answer:

> "Using otto-data, what's the current basis on NVDA and how does it compare to its 14-day overnight average?"

You should see it call `hood_basis_snapshot` and `hood_gaps_summary`, then answer with live numbers.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ottodata.gitbook.io/ottodata-docs/mcp-for-ai-agents/install-in-your-client.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.