# VK WorkSpace (VK Teams): is the website ready for AI agents

> We checked the VK WorkSpace (VK Teams) website (workspace.vk.ru): can ChatGPT, Claude and Alice open it, does it have llms.txt, Markdown, an API and MCP. 70.1 out of 100. API: yes, MCP: no, llms.txt: no.

Источник: https://pachca.com/en/agent-ready/vk-workspace

[workspace.vk.ru](https://workspace.vk.ru)·checked November 11, 2026

70.1out of 100

Ready

Agents can find the site, read it and connect.

Paste the task into Claude Code, Cursor or another agent with access to the site’s code.

- Agent access:  100

- Discoverability:  85

- Content for models:  11

- AI bot rules:  64

- API and protocols:  —

### Fix these first

First, what gets in agents’ way the most.

1.  01

    #### The site serves Markdown when an agent asks

    Failed

    When the homepage is requested with “Accept: text/markdown”, return Markdown with “Content-Type: text/markdown” and “Vary: Accept”. Keep serving HTML for ordinary requests.

    An agent can ask for a page in Markdown instead of HTML and spend far less of its budget on markup.

    [Markdown for agents →](https://pachca.com/en/agent-ready/guide/markdown)

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Response code

    200

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding, Referer

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -H "Accept: text/markdown" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

2.  02

    #### Pages have Markdown versions

    Failed

    Serve a Markdown version of pages at the URL ending in .md and reference it with <link rel="alternate" type="text/markdown"> on the page itself.

    The same page at a URL ending in .md: clean text with no menus or scripts.

    [Markdown for agents →](https://pachca.com/en/agent-ready/guide/markdown)

    ›What the site returned

    URL

    [https://workspace.vk.ru/index.md](https://workspace.vk.ru/index.md)

    Response code

    404

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -H "Accept: text/markdown" -D - -o /dev/null "https://workspace.vk.ru/index.md"
    ```

3.  03

    #### llms.txt exists

    Failed

    Put an llms.txt in Markdown at the site root: a top-level heading with the product name, a short description and a list of links to key pages. The links must resolve.

    A short file for language models: what the product is and where the key pages are.

    [llms.txt →](https://pachca.com/en/agent-ready/guide/llms-txt)

    ›What the site returned

    URL

    [https://workspace.vk.ru/llms.txt](https://workspace.vk.ru/llms.txt)

    Response code

    404

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -H "Accept: text/markdown" -D - -o /dev/null "https://workspace.vk.ru/llms.txt"
    ```

4.  04

    #### robots.txt has rules for AI bots

    Failed

    Add separate User-agent groups for AI bots to robots.txt: GPTBot, ClaudeBot, OAI-SearchBot, PerplexityBot, YandexAdditional. Naming two is enough.

    AI bots are listed by name. Whether you allow or block them, it shows the choice was made.

    [robots.txt for AI →](https://pachca.com/en/agent-ready/guide/robots-txt)

    ›What the site returned

    URL

    [https://workspace.vk.ru/robots.txt](https://workspace.vk.ru/robots.txt)

    Response code

    200

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/robots.txt"
    ```

5.  05

    #### Alice AI robots are allowed

    Partial

    Add a group to robots.txt with “User-agent: YandexAdditional” and “User-agent: YandexAdditionalBot” and an “Allow: /” rule.

    The YandexAdditional robots bring a site into Alice AI answers. Best to allow them with a rule of their own.

    [robots.txt for AI →](https://pachca.com/en/agent-ready/guide/robots-txt)

    ›What the site returned

    URL

    [https://workspace.vk.ru/robots.txt](https://workspace.vk.ru/robots.txt)

    Response code

    200

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/robots.txt"
    ```

Other issues7

1.  06

    #### The site points agents to its machine-readable files

    Failed

    Add a Link header or a <link> tag on the homepage pointing to llms.txt, the page’s Markdown version (rel="alternate" type="text/markdown") or the API description (rel="service-desc").

    Links in the response header or page code lead to llms.txt, a Markdown version or an API description.

    [Markdown for agents →](https://pachca.com/en/agent-ready/guide/markdown)

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

2.  07

    #### llms-full.txt exists

    Failed

    Put an llms-full.txt at the site root with the full text of the site or docs in Markdown.

    The full text of the site or docs in one file. An agent reads it in a single request.

    [llms.txt →](https://pachca.com/en/agent-ready/guide/llms-txt)

    ›What the site returned

    URL

    [https://workspace.vk.ru/llms-full.txt](https://workspace.vk.ru/llms-full.txt)

    Response code

    404

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -H "Accept: text/markdown" -D - -o /dev/null "https://workspace.vk.ru/llms-full.txt"
    ```

3.  08

    #### Content use is declared

    Failed

    Add a “Content-Signal: search=yes, ai-input=yes, ai-train=yes” line to robots.txt. Choose yes or no for each value yourself.

    The Content-Signal line says whether your text may be used for search, AI answers and model training.

    [robots.txt for AI →](https://pachca.com/en/agent-ready/guide/robots-txt)

    ›What the site returned

    URL

    [https://workspace.vk.ru/robots.txt](https://workspace.vk.ru/robots.txt)

    Response code

    200

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/robots.txt"
    ```

4.  09

    #### Pricing is available in Markdown

    Failed

    Serve the pricing page in Markdown: at the page URL ending in .md or at /pricing.md. The file must contain prices.

    An agent comparing products reads pricing most easily from a plain text file.

    [Markdown for agents →](https://pachca.com/en/agent-ready/guide/markdown)

    ›What the site returned

    URL

    [https://workspace.vk.ru/tariffs.md](https://workspace.vk.ru/tariffs.md)

    Response code

    404

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/tariffs.md"
    ```

5.  10

    #### A clear heading structure

    Partial

    Keep a single h1 on the homepage, add h2 headings, do not skip levels (h3 follows h2, not h4) and wrap the main content in a <main> tag.

    One main heading, subheadings in order and a marked main area. An agent uses them to split the page into parts.

    [Access without CAPTCHA or JS →](https://pachca.com/en/agent-ready/guide/site-access)

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    H1 headings: 1

    H2 headings: 14

    has <main>: yes

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

6.  11

    #### The homepage links to API docs

    Partial

    Link to your API docs from the homepage, for example in the footer or a developers menu.

    When asked to set up an integration, an agent looks for docs starting from the homepage.

    [sitemap and JSON-LD →](https://pachca.com/en/agent-ready/guide/structured-data)

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

7.  12

    #### Page preview data is filled in

    Partial

    Add og:title, og:description, og:image and og:type tags to the homepage <head>.

    Title, description, image and page type (Open Graph). An assistant uses them when it shows a link to you.

    [sitemap and JSON-LD →](https://pachca.com/en/agent-ready/guide/structured-data)

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    found: og:title, og:description, og:image

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

What already works25

- #### Homepage opens without a CAPTCHA

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Response code

    200

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding, Referer

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Text is visible without JavaScript

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    words of text: 1,745

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Prices are visible without JavaScript

    ›What the site returned

    URL

    [https://workspace.vk.ru/tariffs/](https://workspace.vk.ru/tariffs/)

    Response code

    200

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding, Referer

    Found

    snippet: лючения Пользователи SaaS Базовый Для команд до 300 человек 309 ₽ за пользователя в месяц 3090 ₽ в месяц

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/tariffs/"
    ```

- #### A missing page returns 404

    ›What the site returned

    URL

    [https://workspace.vk.ru/agent-readiness-check-f91929b9e9/](https://workspace.vk.ru/agent-readiness-check-f91929b9e9/)

    Response code

    404

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/agent-readiness-check-f91929b9e9/"
    ```

- #### A short path from http to https

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Response code

    200

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding, Referer

    Found

    redirects: 1

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### The homepage is light and fast

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    page size, KB: 610

    response time, s: 1.442

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### robots.txt exists

    ›What the site returned

    URL

    [https://workspace.vk.ru/robots.txt](https://workspace.vk.ru/robots.txt)

    Response code

    200

    Headers

    content-type: text/plain; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Referer

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/robots.txt"
    ```

- #### A sitemap exists

    ›What the site returned

    URL

    [https://workspace.vk.ru/sitemap.xml](https://workspace.vk.ru/sitemap.xml)

    Response code

    200

    Headers

    content-type: application/xml

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Referer

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/sitemap.xml"
    ```

- #### Homepage metadata is filled in

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Company or product markup is present

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    JSON-LD types: AggregateOffer, AggregateRating, Answer, Brand, BreadcrumbList, ContactPoint, FAQPage, ListItem, Offer, OfferCatalog, Organization, PostalAddress, Product, Question, Service

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Agents and AI search are allowed

    ›What the site returned

    URL

    [https://workspace.vk.ru/robots.txt](https://workspace.vk.ru/robots.txt)

    Response code

    200

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/robots.txt"
    ```

- #### The homepage is not hidden from search

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Homepage text fits an agent’s memory

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    tokens, approx.: 4,955

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Content starts near the top of the page

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    text before the heading, %: 0

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### ChatGPT and Claude get the same page people do

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Response code

    200

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding, Referer

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Company markup has a description and contacts

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    found: description, logo, contact

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Markup links to official profiles

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    sameAs links: 3

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### About, contact and policy pages are linked from the homepage

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    found: about, contacts, privacy

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### AI search gets the same page people do

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Response code

    200

    Headers

    content-type: text/html; charset=utf-8

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding, Referer

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### The sitemap carries update dates

    ›What the site returned

    URL

    [https://workspace.vk.ru/sitemap.xml](https://workspace.vk.ru/sitemap.xml)

    Response code

    200

    Headers

    content-type: application/xml

    vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Referer

    Found

    share, %: 100

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/sitemap.xml"
    ```

- #### Prices are in the markup

    ›What the site returned

    URL

    [https://workspace.vk.ru/tariffs/](https://workspace.vk.ru/tariffs/)

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/tariffs/"
    ```

- #### Questions and answers are marked up

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Images have text descriptions

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Found

    share, %: 91

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### The page does not forbid quoting its text

    ›What the site returned

    URL

    [https://workspace.vk.ru/](https://workspace.vk.ru/)

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/"
    ```

- #### Pricing and docs are not closed to agents

    ›What the site returned

    URL

    [https://workspace.vk.ru/robots.txt](https://workspace.vk.ru/robots.txt)

    Response code

    200

    Repeat the check yourself

    ```
    curl -sSL -c /dev/null -A "agent-readiness-index/0.1" -D - -o /dev/null "https://workspace.vk.ru/robots.txt"
    ```

Not scored17

These checks do not apply to the site and do not lower the score.

- Open API docs or an MCP server exist
- An API description (OpenAPI) is published
- An MCP server exists
- An agent can find how to sign in
- The API reports errors in a machine format
- An API catalog exists
- Agent skills are published
- The API says which server grants access
- llms.txt is structured well enough to navigate
- The Markdown version has a header with page data
- The MCP server answers a connection
- MCP tools have descriptions
- An access refusal says where to sign in
- An agent-to-agent card exists
- There is a guide for how an agent gets access
- A catalog of AI interfaces exists
- The site does not forbid using its text in AI answers

## Check your own site

Paste the address and get the same breakdown in half a minute.

[Check a site →](https://pachca.com/en/agent-ready)

## Other checked sites

- [CommuniGate Pro](https://pachca.com/en/agent-ready/communigate-pro)47.1
- [Compass](https://pachca.com/en/agent-ready/compass)63.9
- [DION](https://pachca.com/en/agent-ready/dion)40.4
- [eXpress](https://pachca.com/en/agent-ready/express)62.9
- [iMind](https://pachca.com/en/agent-ready/imind)77
- [Loop](https://pachca.com/en/agent-ready/loop)68.5
- [MAX for Business](https://pachca.com/en/agent-ready/max)45.9
- [MTS Link](https://pachca.com/en/agent-ready/mts-link)64.9
- [Pachca](https://pachca.com/en/agent-ready/pachca)97.9
- [Squadus (MyOffice)](https://pachca.com/en/agent-ready/squadus)53.7
- [TamTam](https://pachca.com/en/agent-ready/tamtam)39
- [TrueConf](https://pachca.com/en/agent-ready/trueconf)62.8
- [Yandex 360 (Messenger)](https://pachca.com/en/agent-ready/yandex-360)55.9