A TypeScript implementation of a simple MCP server that exposes datetime information to agentic systems and chat REPLs
Xonta MAX is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
MAX messenger bots and mini-apps in English or Russian: Bot API, code checks, Telegram migration
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user xonta-max-mcp '--' uvx xonta-max-mcp
# 2 — ask your agent for something these tools do
# max_api_reference, max_endpoint_info, max_limits and 26 more
Xonta MAX costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user xonta-max-mcp '--' uvx xonta-max-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://mcp.xonta.ru/max/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http xonta-max-mcp https://mcp.xonta.ru/max/mcpNothing is required, but it can take MAX_BOT_TOKEN (Optional. Your MAX bot token: enables tools that act as your bot (send messages, webhook, commands)), MAX_CA_FILE (Path to the Russian Trusted Root CA (Минцифры) PEM, needed to reach platform-api2.max.ru), XONTA_MAX_LANG (Default answer language: ru (default) or en) if you want to set them.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
29 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Look up current facts about the MAX Bot API and Mini Apps (MAX Bridge) with links to dev.max.ru.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Free text in English or Russian, e.g. 'webhook certificate', 'callback answer', 'initData', 'GET /chats', 'attachment.not.ready' |
| topic | no | Return one whole topic instead of searching | |
| lang | no | — |
Details of one MAX Bot API method (query params, body, limits, gotchas, docs link) or the full method list.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| verb | string | no | HTTP method: GET, POST, PUT, PATCH, DELETE. Omit to list all endpoints |
| path | string | no | Path like '/messages', '/chats/{chatId}/pin' or a concrete one '/chats/-123/pin' |
| lang | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lang | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lang | no | — |
Check MAX bot or mini-app code for known mistakes, with line numbers and fixes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | Source code of a MAX bot or mini-app (any language), or a config / curl snippet |
| lang | no | — |
Plan a port of a Telegram bot or Web App to MAX.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | no | Telegram bot source (aiogram, python-telegram-bot, telebot, Telegraf, grammY, raw HTTP…). Omit to get only the method map |
| lang | no | — |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| language | string | no | python (httpx, no official SDK), typescript (@maxhub/max-bot-api) or go (official client v2) |
| lang | no | — |
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…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| body | object | yes | NewMessageBody JSON: {text, format, attachments, link, notify} |
| target | string | no | message — POST /messages, comment — POST /messages/{id}/comments |
| chat_type | string | no | Where it goes, for channel-specific rules |
| lang | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | no | Message text, up to 4000 characters |
| format | string | no | Text markup |
| buttons | array | no | Rows of buttons. Short form: {text, payload} → callback, {text, url} → link, {text, web_app, payload?} → open_app; or full {type, text, ...} |
| image_urls | array | no | External image URLs to attach without uploading |
| reply_to_mid | string | no | Reply to this message id |
| chat_id | integer | no | For the curl example |
| user_id | integer | no | For the curl example, private dialog |
| disable_link_preview | boolean | no | — |
| lang | no | — |
Split text into MAX messages of at most 4000 characters, cutting at paragraphs, lines or sentences.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Long text to send |
| limit | integer | no | Max characters per message |
| lang | no | — |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Formatted text |
| source | string | yes | Where the text comes from; 'markdown' = ordinary Markdown (e.g. LLM output) |
| target | string | no | MAX format to produce |
| lang | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | start — open bot with payload; startapp — open mini-app; share — 'send to MAX' link for any site, no bot needed; mention — user mention markup |
| bot_name | string | no | Bot public name as in max.ru/<name> (start, startapp) |
| payload | string | no | start: ≤128 chars; startapp: ≤512, A-Za-z0-9_- only |
| text | string | no | share: text to prefill; mention: display name |
| user_id | integer | no | mention: MAX user id |
| button_label | string | no | share: label for the generated HTML button; default depends on lang |
| lang | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| update_type | string | yes | 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_permissi |
| text | string | no | Message text (message_created/edited, comments) or new title |
| payload | string | no | Callback payload or bot_started deep link payload |
| chat_type | string | no | Where it happens |
| chat_id | integer | no | Chat id; default is generated |
| overrides | object | no | Deep-merge into the generated update |
| webhook_url | string | no | If set, also returns a curl command that POSTs the update there |
| secret | string | no | Webhook secret to put into X-Max-Bot-Api-Secret |
| lang | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| test_bot_token | string | no | A TEST token to sign with. Omit to generate a random one. Never pass a production token to a hosted server |
| user_id | integer | no | — |
| first_name | string | no | — |
| chat_type | string | no | Where the mini-app was opened |
| start_param | string | no | Value from ?startapp= |
| age_seconds | integer | no | Make auth_date this many seconds old, to test expiry |
| lang | no | — |
Generate max-bridge-mock.js: a window.WebApp emulator to develop MAX mini-apps in a normal browser on localhost.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| platform | string | no | Platform to emulate: limits which Bridge features work |
| start_param | string | no | Emulated ?startapp= value |
| test_bot_token | string | no | TEST token: initData and requestContact hash will be validly signed with it |
| user_id | integer | no | — |
| first_name | string | no | — |
| phone | string | no | — |
| entry_point | string | no | — |
| lang | no | — |
Check a MAX webhook secret against the rules (5-256 chars, A-Z a-z 0-9 _ -) or generate a strong one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| secret | string | no | Secret to check; omit to generate a new one |
| lang | no | — |
Server version, facts date, mode (hosted or local), languages and whether operator tools are active.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lang | no | — |
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…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| campaign | string | yes | Campaign name, e.g. 'black friday' |
| placements | array | yes | Channels where the ad goes: [{name, cost?, erid?}]. name may be a title or max.ru link |
| bot_name | string | no | Your bot's public name: each placement gets max.ru/<bot>?start=<id> |
| mini_app_bot | string | no | Bot with your mini-app: each placement gets ?startapp=<id> |
| site_url | string | no | Landing page: each placement gets UTM tags and its erid |
| utm_medium | string | no | — |
| promo_codes | boolean | no | Also make one promo code per placement |
| lang | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| placements | array | yes | Per placement: {name, id?, cost, views?, clicks?, starts?, leads?, orders?, revenue?, margin_pct?} |
| events | array | no | Optional bot_started updates, {'payload': …} objects or payload strings; starts are counted per placement id |
| campaign | string | no | Only count payloads of this campaign |
| min_orders | integer | no | Below this many orders a placement is flagged as low data |
| lang | no | — |
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…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Ad post text as it will be published |
| links | array | no | Links used in buttons or elsewhere, if not in the text |
| channel_subscribers | integer | no | Subscribers of the channel where it goes |
| channel_has_a_plus | boolean | no | Whether the channel has the A+ mark (RKN registry) |
| advertiser_site | string | no | Site with the advertiser's details, if they are not in the text |
| lang | no | — |
Verify a MAX signature locally: mini-app initData (two-step HMAC), requestContact phone hash, or the hash of a contact shared through a request_contact button. Explains why a check failed (wrong formula, double decoding, stale auth_date).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | init_data — mini-app launch data; phone — Bridge requestContact() result; contact — contact attachment from a request_contact button |
| init_data | string | no | init_data: raw window.WebApp.initData string |
| hash | string | no | phone/contact: the hash to check |
| phone | string | no | — |
| auth_date | string | no | phone: authDate from requestContact() |
| user_id | string | no | phone: MAX user id |
| vcf_info | string | no | contact: vcf_info exactly as received, JSON-decoded |
| max_age_seconds | integer | no | init_data freshness window |
| bot_token | string | no | Bot token; defaults to MAX_BOT_TOKEN from the environment |
| lang | no | — |
Info about the bot whose token is in MAX_BOT_TOKEN (GET /me): id, name, username, commands.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lang | no | — |
Send a message as your bot (POST /messages). Validates the body first and refuses to send an invalid one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Message text, up to 4000 chars |
| chat_id | integer | no | Group chat or channel id |
| user_id | integer | no | User id for a private dialog |
| format | string | no | — |
| buttons | array | no | Rows of buttons, same short form as max_build_message |
| disable_link_preview | boolean | no | — |
| notify | boolean | no | — |
| lang | no | — |
Recent messages in a chat the bot belongs to (GET /messages), newest first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chat_id | integer | yes | — |
| count | integer | no | — |
| lang | no | — |
Info about one chat or channel (GET /chats/{chatId}) and the bot's own membership and permissions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chat_id | integer | yes | — |
| lang | no | — |
Replace the bot's command list shown to users (PATCH /me/commands).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| commands | array | yes | [{name, description}], up to 32; empty list removes all |
| lang | no | — |
Manage the bot's webhook subscription (GET/POST/DELETE /subscriptions). Checks the URL against MAX rules (https, port 443) before subscribing. Subscribing stops long polling from working.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | list current subscriptions, subscribe a URL, or unsubscribe it |
| url | string | no | https URL on port 443 |
| secret | string | no | subscribe: 5-256 chars A-Za-z0-9_-; generated if omitted |
| update_types | array | no | subscribe: which update types; omit for all |
| lang | no | — |
Fetch pending updates by long polling (GET /updates) to see what the bot receives. Development only;
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| timeout | integer | no | Seconds to wait for new updates |
| marker | integer | no | — |
| lang | no | — |
Call any documented MAX Bot API method as your bot (edit or delete messages, pin, manage admins, comments…).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| verb | string | yes | HTTP method |
| path | string | yes | Documented path, e.g. /chats/-123/pin, /messages |
| query | object | no | Query parameters |
| body | object | no | JSON body |
| lang | no | — |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Xonta MAX or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (29 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 29 recovered tools are registered only when not HOSTED holds (src/xonta_max/server.py:519) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 20.
8 of the 29 recovered tools are registered only when OPERATOR holds (src/xonta_max/server.py:556) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 20.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
20 tools are registered unconditionally · (1) 1 more only when not HOSTED holds (src/xonta_max/server.py:519) · (2) 8 more only when OPERATOR holds (src/xonta_max/server.py:556) — typically when a key or option is configured. All 29 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| max_api_reference | no tags | |
| max_endpoint_info | no tags | |
| max_limits | external-sink | external-sink: keyword "webhook" |
| max_changelog | no tags | |
| max_lint_code | external-sink | external-sink: keyword "webhook" |
| max_migrate_from_telegram | no tags | |
| max_scaffold_bot | external-sink | external-sink: keyword "webhook" |
| max_validate_message | no tags | |
| max_build_message | external-sink | external-sink: keyword "post_message" |
| max_split_text | no tags | |
| max_convert_formatting | no tags | |
| max_deeplink | no tags | |
| max_mock_update | external-sinksensitive-source | external-sink: keyword "webhook", parameter "webhook"; sensitive-source: parameter "secret" |
| max_mock_init_data | no tags | |
| max_bridge_mock | no tags | |
| max_check_webhook_secret | external-sink | external-sink: keyword "webhook" |
| server_status | no tags | |
| max_tracking_links | no tags | |
| max_ad_report | no tags | |
| max_check_ad_post | no tags | |
| max_verify_signature conditional (1) | no tags | |
| max_bot_info conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| max_send_message conditional (2) | external-sink | external-sink: keyword "send_message", declares readOnlyHint: false, openWorldHint: true |
| max_get_messages conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| max_get_chat conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| max_set_commands conditional (2) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| max_webhook conditional (2) | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| max_get_updates conditional (2) | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| max_api_request conditional (2) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Xonta MAX can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.