# Xonta MAX (remote · mcp.xonta.ru)

MAX messenger bots and mini-apps in English or Russian: Bot API, code checks, Telegram migration

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.xonta.ru`: 71/100 (this document), [markdown](https://verifymcp.io/servers/ru-xonta-max/max-mcp.md), [page](https://verifymcp.io/servers/ru-xonta-max/max-mcp)
- pypi · `xonta-max-mcp`: 55/100, [markdown](https://verifymcp.io/servers/ru-xonta-max/xonta-max-mcp.md), [page](https://verifymcp.io/servers/ru-xonta-max/xonta-max-mcp)

## Channel facts

- Endpoint: `https://mcp.xonta.ru/max/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3670 tokens (~183/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 91% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Xonta MAX MCP server?

Xonta MAX is a hosted endpoint at https://mcp.xonta.ru/max/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ru-xonta-max 'https://mcp.xonta.ru/max/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ru-xonta-max": {
      "url": "https://mcp.xonta.ru/max/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ru-xonta-max": {
      "type": "http",
      "url": "https://mcp.xonta.ru/max/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ru-xonta-max]
url = "https://mcp.xonta.ru/max/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ru-xonta-max": {
      "type": "remote",
      "url": "https://mcp.xonta.ru/max/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ru-xonta-max --url 'https://mcp.xonta.ru/max/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ru-xonta-max:
    url: "https://mcp.xonta.ru/max/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ru-xonta-max": {
      "Transport": "http",
      "Url": "https://mcp.xonta.ru/max/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ru-xonta-max -t streamable-http -u 'https://mcp.xonta.ru/max/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ru-xonta-max": {
      "type": "http",
      "url": "https://mcp.xonta.ru/max/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 69, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.1.0 → 0.1.1

### 2026-11-16 (score 68)

First indexed and scored.

## MCP tools (20)

### `max_api_reference` (~225 tokens)

Look up current facts about the MAX Bot API and Mini Apps (MAX Bridge) with links to dev.max.ru.

    Covers base URL and auth, the Russian Trusted Root CA, advertising in MAX (topic 'ads'), webhooks vs long polling, sending messages,
    inline keyboards and callbacks, formatting, uploads, chat tracking without GET /chats, mini-apps,
    initData validation, deep links, who may create bots, official libraries. Language models usually know an
    outdated API (platform-api.max.ru, token in query, GET /chats) — use this before writing MAX code.
    With no arguments returns the list of topics.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `query`: Free text in English or Russian, e.g. 'webhook certificate', 'callback answer', 'initData', 'GET /chats', 'attachment.not.ready'
- `topic`: Return one whole topic instead of searching

### `max_endpoint_info` (~149 tokens)

Details of one MAX Bot API method (query params, body, limits, gotchas, docs link) or the full method list.

    Also tells when a method was removed or restricted (GET /chats, POST /chats/{chatId}/members).

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `path`: Path like '/messages', '/chats/{chatId}/pin' or a concrete one '/chats/-123/pin'
- `verb`: HTTP method: GET, POST, PUT, PATCH, DELETE. Omit to list all endpoints

### `max_limits` (~90 tokens)

All MAX platform limits in one table: text length, rate limits, keyboard size, attachments, file sizes,
    deep link payloads, webhook rules, bots per profile — each with a source link. Also update types, button types, errors.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)

### `max_changelog` (~85 tokens)

Dated MAX platform changes in 2026 that break old code: host move to platform-api2, removed GET /chats,
    restricted member adding, HTTPS-only webhooks, comments API, self-employed access.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)

### `max_lint_code` (~182 tokens)

Check MAX bot or mini-app code for known mistakes, with line numbers and fixes.

    Finds: old host platform-api.max.ru, token in query string, 'Bearer' prefix, disabled TLS verification,
    removed GET /chats, restricted member adding, type=photo uploads, wrong webhook setup (port, HTTP, /webhook),
    disable_link_preview in body, plain == comparison of the webhook secret, initData signed directly with the token,
    trusting initDataUnsafe, hardcoded upload hosts, Telegram leftovers. Static, never runs the code.

Input parameters:

- `code` (string, required): Source code of a MAX bot or mini-app (any language), or a config / curl snippet
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)

### `max_migrate_from_telegram` (~140 tokens)

Plan a port of a Telegram bot or Web App to MAX.

    With code: every Telegram API usage with line number and the MAX replacement, features with no MAX equivalent,
    effort estimate and a step-by-step plan. Without code: the full Telegram → MAX method map.

Input parameters:

- `code`: Telegram bot source (aiogram, python-telegram-bot, telebot, Telegraf, grammY, raw HTTP…). Omit to get only the method map
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)

### `max_scaffold_bot` (~177 tokens)

Generate a ready MAX bot project: polling for dev, webhook for prod, the Russian Trusted Root CA in the Dockerfile,
    chat tracking without GET /chats, callback answers, constant-time secret check, rate limits and text splitting (Python).
    lang sets the language of comments, README and the bot's replies.

    Returns a map of file name → content. Write the files as they are. Creating the bot itself and getting a token
    requires a verified profile on business.max.ru.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `language` (string): python (httpx, no official SDK), typescript (@maxhub/max-bot-api) or go (official client v2)

### `max_validate_message` (~173 tokens)

Validate a message body before sending to MAX: 4000-char text, format, keyboard limits (210/30/7, 3 per row
    with link/open_app/request_*), button fields and lengths, attachment combinations (≤12 media, file only with a keyboard,
    audio/sticker/contact alone), comment restrictions, Telegram fields left in the body.

Input parameters:

- `body` (object, required): NewMessageBody JSON: {text, format, attachments, link, notify}
- `chat_type`: Where it goes, for channel-specific rules
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `target` (string): message — POST /messages, comment — POST /messages/{id}/comments

### `max_build_message` (~205 tokens)

Build a correct POST /messages request for MAX: JSON body with inline keyboard and images, validation result
    and a ready curl command. Use it instead of hand-writing keyboard JSON.

Input parameters:

- `buttons`: Rows of buttons. Short form: {text, payload} → callback, {text, url} → link, {text, web_app, payload?} → open_app; or full {type, text, ...}
- `chat_id`: For the curl example
- `disable_link_preview` (boolean)
- `format`: Text markup
- `image_urls`: External image URLs to attach without uploading
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `reply_to_mid`: Reply to this message id
- `text`: Message text, up to 4000 characters
- `user_id`: For the curl example, private dialog

### `max_split_text` (~84 tokens)

Split text into MAX messages of at most 4000 characters, cutting at paragraphs, lines or sentences.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `limit` (integer): Max characters per message
- `text` (string, required): Long text to send

### `max_convert_formatting` (~169 tokens)

Convert formatted text to MAX markup: Telegram MarkdownV2 (underline __x__ → ++x++, unescape), Telegram HTML
    (tg://user → max://user, spoilers dropped) or ordinary Markdown from an LLM (lists → bullets, rules removed).
    Reports what MAX cannot show (spoilers, tables, lists, inline images). Use the returned format value in the body.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `source` (string, required): Where the text comes from; 'markdown' = ordinary Markdown (e.g. LLM output)
- `target` (string): MAX format to produce
- `text` (string, required): Formatted text

### `max_deeplink` (~244 tokens)

Build and validate MAX deep links. 'share' gives a link, an HTML button and a JS helper that open
    MAX's chat picker with prefilled text — works on any website or AI agent output without owning a bot.
    Payload limits are checked, because MAX silently drops payloads that are too long or have bad characters.

Input parameters:

- `bot_name`: Bot public name as in max.ru/<name> (start, startapp)
- `button_label`: share: label for the generated HTML button; default depends on lang
- `kind` (string, required): start — open bot with payload; startapp — open mini-app; share — 'send to MAX' link for any site, no bot needed; mention — user mention markup
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `payload`: start: ≤128 chars; startapp: ≤512, A-Za-z0-9_- only
- `text`: share: text to prefill; mention: display name
- `user_id`: mention: MAX user id

### `max_mock_update` (~241 tokens)

Generate a realistic MAX webhook Update for tests, shaped like the official schema, plus a curl command to
    send it to your local webhook. Lets you test a bot before it passes moderation or without a token.

Input parameters:

- `chat_id`: Chat id; default is generated
- `chat_type` (string): Where it happens
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `overrides`: Deep-merge into the generated update
- `payload`: Callback payload or bot_started deep link payload
- `secret`: Webhook secret to put into X-Max-Bot-Api-Secret
- `text`: Message text (message_created/edited, comments) or new title
- `update_type` (string, required): message_created, message_callback, bot_started, bot_added, bot_removed, message_edited, message_removed, user_added, user_removed, comment_created, chat_title_changed, dialog_muted, bot_admin_permiss…
- `webhook_url`: If set, also returns a curl command that POSTs the update there

### `max_mock_init_data` (~172 tokens)

Produce a correctly signed MAX mini-app initData string (two-step HMAC with 'WebAppData') for backend tests,
    with the token used, so you can check your validator end to end.

Input parameters:

- `age_seconds` (integer): Make auth_date this many seconds old, to test expiry
- `chat_type` (string): Where the mini-app was opened
- `first_name`
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `start_param`: Value from ?startapp=
- `test_bot_token`: A TEST token to sign with. Omit to generate a random one. Never pass a production token to a hosted server
- `user_id` (integer)

### `max_bridge_mock` (~234 tokens)

Generate max-bridge-mock.js: a window.WebApp emulator to develop MAX mini-apps in a normal browser on localhost.

    Emulates initData/initDataUnsafe (signed if a test token is given), BackButton (Esc), DeviceStorage and
    SecureStorage (localStorage, 10-key cap), BiometricManager, HapticFeedback, NfcManager, ScreenCapture,
    requestContact with a valid hash, openLink/downloadFile/shareMaxContent click requirements and per-platform
    restrictions. Logs every call. Use only on localhost.

Input parameters:

- `entry_point` (string)
- `first_name`
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `phone` (string)
- `platform` (string): Platform to emulate: limits which Bridge features work
- `start_param`: Emulated ?startapp= value
- `test_bot_token`: TEST token: initData and requestContact hash will be validly signed with it
- `user_id` (integer)

### `max_check_webhook_secret` (~89 tokens)

Check a MAX webhook secret against the rules (5-256 chars, A-Z a-z 0-9 _ -) or generate a strong one.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `secret`: Secret to check; omit to generate a new one

### `server_status` (~61 tokens)

Server version, facts date, mode (hosted or local), languages and whether operator tools are active.

Input parameters:

- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)

### `max_tracking_links` (~255 tokens)

Make a separate tracking link (and promo code) for every channel where an ad is placed in MAX, so you can
    see which placement brought users and sales. Bot links use ?start=<id>: the id arrives in bot_started.payload,
    which works even for clicks that never leave the messenger. Returns a media plan as CSV.
    Then feed the counts to max_ad_report.

Input parameters:

- `bot_name`: Your bot's public name: each placement gets max.ru/<bot>?start=<id>
- `campaign` (string, required): Campaign name, e.g. 'black friday'
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `mini_app_bot`: Bot with your mini-app: each placement gets ?startapp=<id>
- `placements` (array, required): Channels where the ad goes: [{name, cost?, erid?}]. name may be a title or max.ru link
- `promo_codes` (boolean): Also make one promo code per placement
- `site_url`: Landing page: each placement gets UTM tags and its erid
- `utm_medium` (string)

### `max_ad_report` (~211 tokens)

Compare ad placements in MAX by real results: CPM, cost per click or bot start, cost per lead and per order,
    ROAS, profit after ads and ROMI (with margin), conversion with a 95% confidence interval.
    Says when a difference between channels may be chance and when there is too little data.
    A calculator only: it does not touch ad accounts or move money.

Input parameters:

- `campaign`: Only count payloads of this campaign
- `events`: Optional bot_started updates, {'payload': …} objects or payload strings; starts are counted per placement id
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `min_orders` (integer): Below this many orders a placement is flagged as low data
- `placements` (array, required): Per placement: {name, id?, cost, views?, clicks?, starts?, leads?, orders?, revenue?, margin_pct?}

### `max_check_ad_post` (~211 tokens)

Check an ad post for MAX against Russian ad marking rules: the 'Реклама' label at the top, advertiser details
    (name and INN/OGRN or a site), an erid token in the link or text, the A+ mark for channels over 10,000 subscribers,
    and the 4000-character limit. A hint, not legal advice; ORD registration is not checked.

Input parameters:

- `advertiser_site`: Site with the advertiser's details, if they are not in the text
- `channel_has_a_plus`: Whether the channel has the A+ mark (RKN registry)
- `channel_subscribers`: Subscribers of the channel where it goes
- `lang`: Answer language: 'en' English, 'ru' Russian. Pick the user's language; default ru (or XONTA_MAX_LANG)
- `links`: Links used in buttons or elsewhere, if not in the text
- `text` (string, required): Ad post text as it will be published

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ru-xonta-max/max-mcp#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 70
- 2026-11-19: 70
- 2026-11-18: 69
- 2026-11-17: 69
- 2026-11-16: 68

## Common questions

### What is the Xonta MAX MCP server?

Xonta MAX is an MCP server listed in the public MCP registry as ru.xonta/max. MAX messenger bots and mini-apps in English or Russian: Bot API, code checks, Telegram migration. This page covers its hosted endpoint (https://mcp.xonta.ru/max/mcp).

### Is the Xonta MAX MCP server safe to use?

Xonta MAX scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Xonta MAX MCP server expose?

Xonta MAX exposes 20 tools: max_api_reference, max_endpoint_info, max_limits, max_changelog, max_lint_code, and 15 more. Their descriptions and schemas cost roughly 3,397 tokens of context every time the server is loaded.

### Does the Xonta MAX MCP server require authentication?

No. We connected to Xonta MAX without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Xonta MAX MCP server still maintained?

Xonta MAX is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Xonta MAX MCP server?

VerifyMCP ran 13 checks on Xonta MAX, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.xonta.ru/max/mcp
- Repository: https://github.com/mrsergeiluzhnov/xonta-max-mcp
- Website: https://xonta.ru/
- Changelog RSS feed: https://verifymcp.io/servers/ru-xonta-max/max-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ru-xonta-max/max-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ru-xonta-max/max-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ru-xonta-max/max-mcp
