> For the complete documentation index, see [llms.txt](https://docs.idlayr.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.idlayr.com/help-center/readme/ai-assistants.md).

# Using the docs with an AI assistant

The IDlayr documentation is exposed as an [MCP](https://modelcontextprotocol.io) server. Any MCP-aware AI assistant — Claude Code, Cursor, Continue, VS Code with MCP support, and others — can be pointed at the docs and answer questions grounded in the live content.

The endpoint is:

```
https://docs.idlayr.com/~gitbook/mcp
```

## What the assistant can do

The MCP server exposes four tools to the assistant:

* **Search** the documentation for anything — product names, endpoints, error codes, guides.
* **Read** a specific documentation page in full.
* **Ask a natural-language question** and receive a synthesized answer with source links back to the docs.
* **Send feedback** to the docs team when the assistant spots something outdated, missing, or wrong.

Content is always fetched live, so the assistant sees the latest version of each page — not a cached snapshot.

## Setup

### Claude Code

Run this once in your terminal:

```bash
claude mcp add gitbook-documentation --scope user --transport http https://docs.idlayr.com/~gitbook/mcp
```

Restart Claude Code. The `mcp__gitbook-documentation__*` tools become available in every session.

### Cursor

Add the server to your global `~/.cursor/mcp.json` (or the project-scoped `.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "gitbook-documentation": {
      "url": "https://docs.idlayr.com/~gitbook/mcp"
    }
  }
}
```

Restart Cursor. The tools are available under **MCP Tools** in the chat.

### Other clients

Any MCP client that supports the streamable-HTTP transport can connect. Point it at `https://docs.idlayr.com/~gitbook/mcp` — no auth is required.

## Working with an assistant

A few patterns that tend to work well:

* **"How do I integrate Secure SNA on iOS?"** — the assistant will find the relevant pages, quote the code, and cite the source URLs. Ask follow-ups to drill in.
* **"What error codes does the Reverse SMS API return?"** — the assistant will pull from both the per-product error page and the shared errors reference.
* **"Show me the migration steps from PhoneCheck v0.2 to Secure SNA v1"** — it will fetch the migration guide and the breaking-changes page and stitch them together.

Because the assistant can also read individual pages, you can also point it directly: *"read* [*docs.idlayr.com/guides/high-assurance-signup*](https://docs.idlayr.com/guides/high-assurance-signup) *and adapt the pattern for our onboarding flow."*

## Reporting docs issues

If you (or the assistant) spot something wrong on a page — an outdated code sample, a stale product name, a contradictory statement — the assistant can send feedback directly through the MCP endpoint. The report lands with the IDlayr docs team.

You can also open an issue with your IDlayr account team — see [Support](/help-center/readme/support.md).


---

# 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://docs.idlayr.com/help-center/readme/ai-assistants.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.