Multi-MCP AI Agent

Name: Multi-MCP AI Agent
Author: aviban15

@aviban15

Multi-MCP AI Agent について

An AI agent which utilizes multiple MCP servers, including internal tools like math tools, and external tools like Google services and web scraping.

#mathgpt #math-solver #math-assistant

基本情報

カテゴリ

AI とエージェント

ライセンス

MIT license

ランタイム

python

トランスポート

stdio

公開者

aviban15

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "multi-mcp-agent": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Multi-MCP AI Agent?

An agentic AI system that coordinates multiple MCP (Model Control Protocol) servers to deliver capabilities ranging from basic math to Google Workspace and web scraping. It includes a Telegram bot interface and Server-Sent Events (SSE) for real-time communication, targeting developers building modular AI agents.

How to use Multi-MCP AI Agent?

After cloning the repository, create a virtual environment with uv venv, activate it, install dependencies with uv sync, and set up environment variables for Gemini API key, Telegram bot token, and Google OAuth credentials. Start the agent with uv run agent.py or the Telegram bot server with uv run telegram_sse_server.py. Configure MCP servers in config/profiles.yaml and models in config/models.json.

Key features of Multi-MCP AI Agent

Multi-MCP architecture for distributed processing
Cognitive modules: perception, memory, decision, action
Google Workspace integration (Gmail, Drive, Sheets)
Web scraping, content extraction, DuckDuckGo search
Real-time Telegram bot and SSE communication
Session handling, context management, strategic decision making

Use cases of Multi-MCP AI Agent

Automating document processing with semantic search and content extraction
Fetching real-time data from web searches and Google Workspace
Building a conversational assistant with Telegram bot interface
Orchestrating multiple MCP services for complex multi-step tasks

FAQ from Multi-MCP AI Agent

What external services does Multi-MCP AI Agent integrate with?

It integrates with Google Workspace (Gmail, Google Drive, Google Sheets), DuckDuckGo search, and web scraping/content extraction services.

What are the prerequisites to run Multi-MCP AI Agent?

Python 3.11+, UV package manager, a Telegram Bot Token (for bot functionality), and Google Cloud credentials (for Google Workspace integration).

How do I start the agent and the Telegram server?

Use uv run agent.py for the main agent and uv run telegram_sse_server.py to start the Telegram bot server with SSE support.

Which MCP servers are included in Multi-MCP AI Agent?

Four servers: Basic Operations (math, image processing, file ops), Document Processing (indexing, search, content extraction, image captioning), Web Integration (DuckDuckGo search, web content fetching, rate-limited requests), and Google Workspace (Gmail, Sheets, Drive, URL scraper).

Does Multi-MCP AI Agent support real-time communication?

Yes, through a Telegram bot interface and Server-Sent Events (SSE) for live event streaming and updates.

「AI とエージェント」の他のコンテンツ

Unreal Engine Generative AI Support Plugin

prajwalshettydev

Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti

622