mcp-server-max
A Model Context Protocol server for Max messenger that lets AI assistants send and read messages, manage chats, and interact with the Max platform API.
README
mcp-server-max
A Model Context Protocol (MCP) server for Max messenger (formerly VK Teams / ICQ).
Lets any MCP-compatible AI assistant (Claude, OpenClaw, etc.) send and read messages, manage chats, and interact with the Max platform API.
Features
| Tool | Description |
|---|---|
send_message |
Send a message (text, markdown, HTML) with reply support |
read_messages |
Read chat history (with time range and pagination) |
list_chats |
List group chats the bot is a member of |
get_chat_info |
Chat details — title, description, members count |
get_chat_members |
List members of a chat |
edit_message |
Edit an existing message |
delete_message |
Delete a message |
pin_message |
Pin a message in a chat |
unpin_message |
Unpin the pinned message |
get_pinned_message |
Get the currently pinned message |
leave_chat |
Leave a group chat |
get_bot_info |
Get information about the bot |
send_typing |
Send typing indicator |
get_updates |
Get recent events via long polling |
Installation
pip install mcp-server-max
Or with uv:
uvx mcp-server-max
Configuration
Getting a bot token
- Open Max messenger
- Find
@MasterBot(or go to Chat-bots section) - Create a new bot and copy the token
Environment variables
| Variable | Required | Description |
|---|---|---|
MAX_BOT_TOKEN |
Yes | Bot token from @MasterBot |
MCP_LOG_LEVEL |
No | Log level: DEBUG, INFO, WARNING, ERROR (default: INFO) |
Usage
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"max": {
"command": "mcp-server-max",
"env": {
"MAX_BOT_TOKEN": "your-bot-token"
}
}
}
}
Claude Code
{
"mcpServers": {
"max": {
"command": "mcp-server-max",
"env": {
"MAX_BOT_TOKEN": "your-bot-token"
}
}
}
}
OpenClaw
Add to openclaw.json:
{
"mcp": {
"servers": {
"max": {
"command": "mcp-server-max",
"env": {
"MAX_BOT_TOKEN": "your-bot-token"
}
}
}
}
}
Direct (stdio)
export MAX_BOT_TOKEN=your-bot-token
mcp-server-max
Examples
Once connected, your AI assistant can:
- Read messages: "What are the latest messages in the team chat?"
- Send messages: "Send 'Meeting at 3pm' to the project chat"
- Manage chats: "Who are the members of the dev chat?"
- Pin messages: "Pin the last important message"
API
This server uses the Max Bot API (https://platform-api.max.ru).
Requirements
- Python 3.10+
- A Max bot token (from @MasterBot)
License
MIT
Links
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.