> For the complete documentation index, see [llms.txt](https://docs.vapinetwork.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.vapinetwork.ai/reference/http-api/feed-and-api-catalog.md).

# Feed and API catalog

Call exposes an Atom feed for new verified listings and an RFC 9727 API catalog for machine-readable discovery.

{% hint style="info" %}
Call is launching. The console does not serve Call yet; this page describes the launch flow.
{% endhint %}

The feed and API catalog make Call discoverable by tools that already understand Atom or RFC 9727. Use the feed for new verified listings and the catalog for machine-readable links to vAPI services.

## Atom feed

### GET /call/feed.xml

Read the 50 newest verified self-listed, partner, and claimed listings, ordered by `listedAt`.

**Auth:** none.

| Query parameter | Description                                       |
| --------------- | ------------------------------------------------- |
| None            | This endpoint has no documented query parameters. |

```bash
curl -H 'Accept: application/atom+xml' 'https://api.vapinetwork.ai/call/feed.xml'
```

The response is an Atom 1.0 document with content type `application/atom+xml`. Each entry links to `/call/:serviceId`. The feed is cached for five minutes.

This captured response is shortened to two entries.

```xml
<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <id>https://api.vapinetwork.ai/call/feed.xml</id>
  <title>New APIs on vAPI Call</title>
  <subtitle>Verified x402 APIs newly listed on vAPI Call.</subtitle>
  <link rel="self" type="application/atom+xml" href="https://api.vapinetwork.ai/call/feed.xml"/>
  <link rel="alternate" type="text/html" href="https://api.vapinetwork.ai/call"/>
  <updated>2026-09-29T14:08:45.991Z</updated>
  <author><name>vAPI Call</name></author>
  <entry>
    <id>https://api.vapinetwork.ai/call/stablephone</id>
    <title>StablePhone</title>
    <link rel="alternate" type="text/html" href="https://api.vapinetwork.ai/call/stablephone"/>
    <published>2026-09-29T14:08:45.991Z</published>
    <updated>2026-09-29T14:08:45.991Z</updated>
    <summary>Have an AI voice agent phone a US or Canadian number and carry out a task. Each call settles $0.54 in USDC on Base over x402.</summary>
  </entry>
  <entry>
    <id>https://api.vapinetwork.ai/call/the-graph</id>
    <title>The Graph</title>
    <link rel="alternate" type="text/html" href="https://api.vapinetwork.ai/call/the-graph"/>
    <published>2026-09-18T15:11:38.136Z</published>
    <updated>2026-09-18T15:11:38.136Z</updated>
    <summary>Send GraphQL queries directly to The Graph&apos;s x402 endpoint. Each request settles $0.01 in USDC on Base.</summary>
  </entry>
</feed>
```

## RFC 9727 API catalog

### GET /.well-known/api-catalog

Read the RFC 9727 linkset that names vAPI discovery, the x402 decoder, the hosted MCP, and related machine-readable documents.

**Auth:** none.

| Request header | Description                     |
| -------------- | ------------------------------- |
| `Accept`       | Use `application/linkset+json`. |

```bash
curl -H 'Accept: application/linkset+json' 'https://api.vapinetwork.ai/.well-known/api-catalog'
```

The response is a linkset with content type `application/linkset+json`.

```json
{
  "linkset": [
    {
      "anchor": "https://api.vapinetwork.ai/.well-known/api-catalog",
      "item": [
        { "href": "https://api.vapinetwork.ai/api/call/discovery", "title": "Call discovery" },
        { "href": "https://api.vapinetwork.ai/x402/decode", "title": "vAPI x402 decoder" },
        { "href": "https://api.vapinetwork.ai/mcp", "title": "vAPI hosted MCP" },
        { "href": "https://api.vapinetwork.ai/a2a", "title": "vAPI A2A agent" }
      ],
      "service-doc": [
        { "href": "https://vapinetwork.ai/llms.txt", "type": "text/plain" }
      ]
    },
    {
      "anchor": "https://api.vapinetwork.ai/x402/decode",
      "service-desc": [
        { "href": "https://api.vapinetwork.ai/x402/openapi.json", "type": "application/json" }
      ],
      "status": [
        { "href": "https://api.vapinetwork.ai/x402/readyz", "type": "application/json" }
      ]
    },
    {
      "anchor": "https://api.vapinetwork.ai/mcp",
      "status": [
        { "href": "https://api.vapinetwork.ai/mcp/health", "type": "application/json" }
      ]
    },
    {
      "anchor": "https://api.vapinetwork.ai/a2a",
      "service-desc": [
        { "href": "https://api.vapinetwork.ai/.well-known/agent-card.json", "type": "application/json" }
      ]
    }
  ]
}
```

### HEAD /.well-known/api-catalog

Check the API catalog headers without downloading the linkset body.

**Auth:** none.

| Request header | Description                    |
| -------------- | ------------------------------ |
| None           | No request header is required. |

```bash
curl -I 'https://api.vapinetwork.ai/.well-known/api-catalog'
```

The headers keep the catalog link. A response body is not used for this request.

The console root and `/api/call/discovery` also send a `Link` header pointing to this catalog.

Checked on 2026-10-02.


---

# 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.vapinetwork.ai/reference/http-api/feed-and-api-catalog.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.