# Developers and AI Agents

> Machine-readable access to AIVA Claims: llms.txt, Markdown alternates of every public page, an OpenAPI 3.1 document, and an MCP server. No API key required.

Source: https://aivaclaims.com/developers

## What is available

AIVA Claims publishes its public content and unauthenticated APIs in machine-readable forms: an llms.txt index, a Markdown alternate of every public page, an OpenAPI 3.1 document, and an MCP server. No account or API key is needed for any of them.

## llms.txt

- [/llms.txt](https://aivaclaims.com/llms.txt) — index of every public page and endpoint, in the [llmstxt.org](https://llmstxt.org/) format.
- [/llms-full.txt](https://aivaclaims.com/llms-full.txt) — every public page as one Markdown document.

## Markdown alternates

Every public page is available as Markdown at the same URL with `.md` appended ([/faq.md](https://aivaclaims.com/faq.md), [/index.md](https://aivaclaims.com/index.md) for the homepage), or by requesting the page with `Accept: text/markdown`. Responses carry `x-markdown-tokens`, an estimate of the document's length in tokens (characters divided by four).

## OpenAPI

- [/openapi.json](https://aivaclaims.com/openapi.json) — OpenAPI 3.1 description of the unauthenticated endpoints (also at [/.well-known/openapi.json](https://aivaclaims.com/.well-known/openapi.json)).

## MCP server

- [https://aivaclaims.com/mcp](https://aivaclaims.com/mcp) — Model Context Protocol server (Streamable HTTP, no authentication). The endpoint documents its own tools.

## Crawling

[/robots.txt](https://aivaclaims.com/robots.txt) allows AI crawlers and declares `Content-Signal: search=yes, ai-train=yes, ai-input=yes`. [/sitemap.xml](https://aivaclaims.com/sitemap.xml) lists every public page.

## Contact

[help@aivaclaims.com](mailto:help@aivaclaims.com)