Skip to content

Turn any site or docs into a clean, always-fresh feed that agents can actually read.

AgentFeeder turns a domain into llms.txt, per-page markdown and a hosted MCP resource server, and re-crawls when your content changes. It is for vendors who want AI assistants to get their product right, and for agent builders.

No account. No card. No sales call.

  • Clean feeds generated from any site or docs
  • Re-crawled and diffed when content changes
  • A hosted MCP resource server

Can an AI agent read your site and get your product right?

Answer fourteen questions about your site or docs: files for agents, the facts assistants get wrong, freshness and serving agents directly. See your score and what to publish first. Runs in your browser. No account, no card, no call.

Your site and documentation

Answer for how things are today. Runs in your browser. Nothing is sent.

Files for agents

Does your site publish an llms.txt file?

Is there an llms-full.txt with the full text of your site or docs in one file?

Is each page available as clean markdown, without navigation or cookie banners?

Do sections have stable anchors that survive when a page is edited?

Facts assistants get wrong

Can your pricing be read from the page without running JavaScript?

Is the current API version stated in text in your docs?

Are your rate limits and plan limits written down in one place?

When you last asked an AI assistant about your pricing, version and limits, was it right?

Freshness

Is there a structured changelog with a date and version on every entry?

Do your agent-facing files update whenever the docs change?

Is someone told when a page that agents rely on changes?

Serving agents directly

Can agents fetch your content through an MCP resource server?

Is your content available as an index an agent builder could embed?

Do you know which agents consume your content, and what they fetch?

Answer the questions to see your score. It updates as you go.

Method: yes scores a question in full, partly scores half and no scores nothing. Each is weighted from one to three by how directly it decides whether an agent gets your product facts right, and the score is the weighted share of the points available. Unanswered questions are left out.

Control how AI represents your product

A feed layer that turns a website into clean, always-fresh representations an assistant or an agent can read without parsing.

llms.txt and llms-full.txt

Point it at a domain and it produces and maintains llms.txt and llms-full.txt for the whole site.

A hosted MCP resource server

Your content is served through a hosted MCP resource server, ready for agents to call.

Per-page markdown

Every page is available as clean markdown with stable anchors, without navigation or cookie banners.

Changelog and version metadata

Structured changelog and version metadata keep pricing, API versions and limits current.

An embeddings-ready index

Content is indexed ready for embeddings, so agent builders can use it as a source straight away.

Re-crawled on change

It re-crawls when your content changes, diffs the result and notifies you.

The problem

An AI assistant asked about a product answers from a stale crawl of a JavaScript-rendered marketing site and gets the pricing, the API version and the limits wrong.

The vendor has no way to correct it.

Meanwhile agent builders burn tokens scraping HTML full of navigation and cookie banners to extract three paragraphs of substance.

Who it is for

  • Developer-tools and SaaS companies

    Vendors with documentation who want AI assistants to get their pricing, API version and limits right.

  • Content businesses

    Publishers who want control over how AI represents what they publish.

  • Agent builders

    Developers who need reliable sources and are tired of scraping HTML for three paragraphs of substance.

How it works

AgentFeeder, from the first step to the result.

  1. 1

    Point it at your domain

    Add the site or documentation you want represented.

  2. 2

    Feeds are generated

    llms.txt, per-page markdown, an MCP resource server and an embeddings-ready index are produced.

  3. 3

    Kept fresh automatically

    Changes trigger a re-crawl, a diff and a notification.

Questions people actually ask

What does AgentFeeder produce?
llms.txt and llms-full.txt, a hosted MCP resource server, per-page markdown with stable anchors, structured changelog and version metadata, and an embeddings-ready index.
How does it stay current?
It re-crawls your site when content changes, diffs the result and notifies you.
Why would a vendor want this?
Assistants often answer from stale crawls of JavaScript-rendered sites and get pricing, API versions and limits wrong. A maintained feed gives them an accurate source you control.
Why would an agent builder want this?
It is a source that does not need parsing, so you are not burning tokens on navigation and cookie banners.
What does it cost?
39 dollars a month per domain for hosted, auto-refreshing feeds with change notifications.
Is there a larger plan?
Yes. 249 dollars a month adds multiple domains, private sources, MCP hosting and analytics on which agents consumed what.
Why should I trust the agent readability check?
The score comes from your answers, worked out in your browser. It does not crawl your site; the free generator does that, producing llms-full.txt for a whole public site from its URL, with no account.

Pricing

Priced per domain, with a multi-domain plan for private sources and agent analytics.

DomainRecommended

Hosted, auto-refreshing feeds for one domain.

$39
per domain, per month
  • Auto-refreshing feeds
  • Change notifications
Get in touch

Multi-domain

For vendors with several sites or private content.

$249
per month
  • Multiple domains
  • Private sources
  • MCP hosting
  • Analytics on which agents consumed what
Talk to us

Prices in USD.

Can an AI agent read your site and get your product right?

Answer fourteen questions about your site or docs: files for agents, the facts assistants get wrong, freshness and serving agents directly. See your score and what to publish first. Runs in your browser. No account, no card, no call.

Open the free tool

It runs in your browser. AgentFeeder never sees your inputs.