# AI & LLM tools

Inqud publishes machine-readable resources so you can work with our docs and API from any AI agent or chat client.

{% hint style="info" %}
Everything below is public. No API key, no VPN.
{% endhint %}

### What's available

<table><thead><tr><th width="134.5390625">Resource</th><th width="326.61328125">URL</th><th>Best for</th></tr></thead><tbody><tr><td><a href="/pages/MJzVxEOKfjj7UYsIab6r">MCP server</a></td><td><a href="https://mcp.inqud.com/v1/mcp">https://mcp.inqud.com/v1/mcp</a></td><td>AI agents and IDEs that support tool use (Claude Code, Cursor, Codex, Windsurf, etc). </td></tr><tr><td>llms.txt</td><td><a href="https://docs.inqud.com/llms.txt">https://docs.inqud.com/llms.txt</a></td><td>A short index of our docs (this website), formatted for LLMs.</td></tr><tr><td>llms-full.txt</td><td><a href="https://docs.inqud.com/llms-full.txt">https://docs.inqud.com/llms-full.txt</a></td><td>The full content of this website as one plain-text file.</td></tr><tr><td>OpenAPI spec</td><td><a href="https://cdn.inqud.com/api/openapi.yml">https://cdn.inqud.com/api/openapi.yml</a></td><td>Machine-readable API contract — for codegen or for handing schemas to an LLM.</td></tr></tbody></table>

### Pick the right one

**Building an integration with AI assistance in your editor** → set up the [MCP server](/developer/ai-and-llm-tools/mcp-server.md) once. The agent will look up endpoints and docs on demand.

**Asking ChatGPT or Claude a one-off question about Inqud** → paste the `llms-full.txt` URL into the chat.

**Generating a typed API client or describing the API schema to a model** → use the OpenAPI spec.

***

### Plain-text exports

If your AI client doesn't speak MCP, you can still feed it Inqud's docs and API spec as plain text.

#### `llms.txt` — docs index

A compact, LLM-friendly index of every page in our documentation.

```
https://docs.inqud.com/llms.txt
```

Paste the URL into a chat and ask the model to use this index to find the right page. Good for short conversations where you want the model to navigate, not memorise.

#### `llms-full.txt` — full docs dump

The full content of every public doc page concatenated into one file.

```
https://docs.inqud.com/llms-full.txt
```

Paste into a chat for any longer integration session — the model gets the entire docs corpus in its context and can answer without follow-up fetches.

Both files are regenerated automatically whenever docs change.

#### OpenAPI spec

The machine-readable contract for the Inqud public API.

```
https://cdn.inqud.com/api/openapi.yml
```

Common uses:

* **Generate a typed client** — feed into `openapi-generator`, `openapi-typescript`, or any equivalent tool.
* **Describe the API to an LLM** — paste the URL or download and attach the file. Models handle OpenAPI 3.x natively.
* **Diff against your integration** — pin the spec in your repo and re-pull on releases to detect contract changes.

#### Example prompt

> Here are Inqud's docs: <https://docs.inqud.com/llms-full.txt> And the API spec: <https://cdn.inqud.com/api/openapi.yml>
>
> I want to charge a recurring subscription monthly. What endpoints do I call, in what order?

Most chat models will fetch both URLs and answer with concrete request examples.


---

# Agent Instructions: 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:

```
GET https://docs.inqud.com/developer/ai-and-llm-tools.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.