Connector guide8-minute read19 MCP tools7 languages

Connect VK Teams to Gemini CLI via MCP: Messages

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

HCBy HelpCode teamUpdated 8 min read Open-source on GitHub

No credit card · 7-day trial · Self-host alternative available

VK Teams

VK Teams

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

tools

19

Region

INTL

Category

Messaging

Authentication

Query Param Auth

Required env vars

VK_TEAMS_API_URLVK_TEAMS_BOT_TOKEN
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Summary

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

Guided setup

Connect VK Teams to Gemini in 2 minutes

Start a free trial on AnythingMCP Cloud, connect VK Teams in the guided setup, then add your MCP URL to Gemini. No code and no server to run.

No credit card · 7-day trial · Self-host alternative available

Try asking

Example prompts for VK Teams

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

VK Teams · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → VK Teams, enter the Bot API address and the bot token from Metabot, mint an MCP API key and you're done. No Docker, no git clone, no local server.

VK Teams + Gemini

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

VK_TEAMS_API_URL, VK_TEAMS_BOT_TOKEN

Step 1 — Get credentials

Setting up takes about 3 minutes.

  1. In VK Teams open a chat with Metabot (search for @metabot) and send /newbot. Choose a name and a nick ending in bot. Metabot answers with the bot token, which looks like 001.2659914704.0218887601:747432131.
  2. Paste the token into VK_TEAMS_BOT_TOKEN. It is sent as the token query parameter of every call, so it shows up in the URL of each request: treat the address below as trusted infrastructure only.
  3. Set VK_TEAMS_API_URL to the Bot API address. For the VK Teams cloud it is https://myteam.mail.ru/bot/v1. An on-premise installation has its own address ending in /bot/v1; your VK Teams administrator knows it. On AnythingMCP Cloud the address must be reachable from the internet.
  4. To let the bot work in a group or channel, allow it to join groups in Metabot (/setjoingroups), then add it as a member (as an administrator for pinning, renaming and the member lists).

Where to start: vk_teams_get_self checks token and address. vk_teams_get_events returns what people wrote to the bot and the ids you need: payload.chat.chatId for a chat and payload.msgId for a message. There is no call that lists the bot's chats, so keep the ids you see.

Messages: vk_teams_send_text (plain, MarkdownV2 or HTML; reply, forward and inline buttons), vk_teams_edit_text, vk_teams_delete_messages (switched off at install). Files: vk_teams_upload_file fetches a file from a URL and sends it; vk_teams_send_file sends a file that is already on the server by its fileId; vk_teams_get_file_info turns a fileId somebody sent into name, size and a download link. vk_teams_answer_callback_query answers a button press, vk_teams_send_chat_actions shows typing.

Groups and channels: vk_teams_get_chat_info, vk_teams_list_chat_admins, vk_teams_list_chat_members, vk_teams_list_blocked_users, vk_teams_list_pending_users, vk_teams_pin_message, vk_teams_unpin_message, vk_teams_set_chat_title and vk_teams_set_chat_about.

Field notes

  • chatId: a person is addressed by user id (in VK Teams usually the corporate e-mail address) or @nick; a group or channel id ends in @chat.agent.
  • msgId is a 64-bit number. Pass it as text exactly as received; the connector also returns such numbers as text so no digit is lost.
  • Events: vk_teams_get_events with last_event_id 0 returns everything waiting. Once you pass a higher id, the server forgets the events up to it, so only do that after handling them. Another program polling the same bot takes events away from this one.
  • The API answers HTTP 200 even for a refusal and reports it as ok: false with a description (for example Invalid token); the connector turns that into an error.
  • Most methods are GET requests, including the ones that send; a message is delivered the moment the call is made.
  • Formatting: with parse_mode MarkdownV2 escape the characters the format reserves, or use HTML, which is easier to get right.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (on Windows %USERPROFILE%\.gemini\settings.json). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}
  1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
  2. Save the file and restart gemini.
  3. Run /mcp inside Gemini CLI (or gemini mcp list in your shell) — anythingmcp should show as connected.
  4. Start prompting — Gemini CLI can now call the VK Teams tools.

Available tools

ToolWhat it does
vk_teams_get_selfRead the bot behind the token: userId, nick, firstName, about and photo. Use it to check the token and the API address. Read-only
vk_teams_get_eventsRead the events waiting for the bot (long polling): events[] with eventId, type (newMessage, editedMessage, deletedMessage, pinnedMessage…
vk_teams_send_textSend a text message as the bot to a user, group or channel, optionally formatted, as a reply, as a forward, or with inline buttons. Returns…
vk_teams_send_fileSend a file that is already on the VK Teams servers, by its fileId, with an optional caption. The fileId comes from an earlier upload…
vk_teams_upload_fileUpload a file from a URL and send it as the bot to a user, group or channel, with an optional caption. The connector downloads the file (up…
vk_teams_edit_textChange the text of a message the bot sent, and optionally its inline buttons. Returns ok. Only the bot's own messages can be edited
vk_teams_delete_messagesDelete one or more messages from a chat for everyone. The bot can delete its own messages within 48 hours and, as an administrator of a…
vk_teams_answer_callback_queryAnswer the press of an inline button (a callbackQuery event): show the user a short notice or an alert, or open a URL. Returns ok. Answer…
vk_teams_send_chat_actionsShow what the bot is doing in a chat for about 10 seconds: typing a message or looking at the chat. Pass an empty list to stop showing it.…
vk_teams_get_chat_infoRead a chat: type (private, group or channel) and, for a person, firstName, lastName, nick, about and isBot; for a group or channel, title…
vk_teams_list_chat_adminsList the administrators of a group or channel: admins[] with userId and creator (true for the owner). The bot must be a member. Read-only
vk_teams_list_chat_membersList the members of a group or channel: members[] with userId and the flags creator and admin, plus cursor when more follow. The bot must…
vk_teams_list_blocked_usersList the users blocked in a group or channel: users[] with userId. The bot must be an administrator there. Read-only
vk_teams_list_pending_usersList the users waiting for approval to join a group or channel with join moderation: users[] with userId. The bot must be an administrator…
vk_teams_pin_messagePin a message in a group or channel so it stays at the top. The bot must be an administrator there. Returns ok
vk_teams_unpin_messageUnpin a pinned message in a group or channel; the message itself stays. The bot must be an administrator there. Returns ok
vk_teams_set_chat_titleChange the title of a group or channel. Every member sees the new title at once, so confirm it with the user. The bot must be an…
vk_teams_set_chat_aboutChange the description (about text) of a group or channel. The bot must be an administrator there. Returns ok
vk_teams_get_file_infoRead the details of a file on the VK Teams servers by its fileId: type (image, video, audio and so on), size in bytes, filename and url, a…

Example prompts

  • "What did people write to the bot since this morning?"
  • "Send the message Release 2.4 is live to the group Dev Announcements."
  • "Who are the admins and members of the channel Sales Team?"
  • "Pin the last message in the group Dev Announcements."
  • "What is in the file Anna sent to the bot, and how large is it?"

FAQ

Where do the token and address come from? Write /newbot to Metabot (@metabot) in VK Teams, choose a name and a nick ending in bot, and copy the token it answers with. The Bot API address of the VK Teams cloud is https://myteam.mail.ru/bot/v1; an on-premise installation has its own address ending in /bot/v1. On AnythingMCP Cloud that address must be reachable from the internet.

What can the bot see and do? Everything happens as the bot: it reads the events sent to it, reaches users who wrote to it first and chats it was added to, sends and edits messages, sends files, answers button presses and reads and manages its groups and channels (pinning, titles and member lists need admin rights). There is no call that lists the bot's chats, and another program polling the same bot takes events away from this one.

Which tools install switched off? vk_teams_delete_messages. Switch it on on the connector page only if the AI should use it. Messages leave the moment the call is made, so the AI shows you each one first.

Where does Gemini CLI look for MCP servers? In ~/.gemini/settings.json for your user, or in .gemini/settings.json inside a project. gemini mcp list shows each server and whether it connects.

Next steps

Was this guide helpful?

Connect VK Teams to Gemini in 2 minutes

Start a free trial on AnythingMCP Cloud, connect VK Teams in the guided setup, then add your MCP URL to Gemini. No code and no server to run.

Related guides

Connectors

Connect VK Teams to ChatGPT via MCP: Messages and Files

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

Connectors

Connect VK Teams to Claude via MCP: Messages and Files

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

Connectors

Connect VK Teams to Microsoft Copilot via MCP

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

Connectors

Connect VK Teams to Cursor via MCP: Messages and Files

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

Connectors

Connect VK Teams to Meta Muse via MCP: Messages

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.

Connectors

VK Teams MCP Server: Messages, Files and Channels

Let your AI work as a bot in VK Teams (VK WorkSpace), in the cloud or on-premise: read incoming messages and events, send and edit messages, send files, answer button presses, and look up and manage groups and channels. Bot token.