Multi-MCP AI Agent

by aviban15

250 downloads

Not rated

GitHub

About

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

Details

Author: aviban15
Downloads: 250
Categories: AI

- 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

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Multi-MCP AI Agent

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

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

JSON

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

JSON

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

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

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

JSON

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

JSON

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

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

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

McpServers

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

Multi-MCP AI Agent

An Agentic AI agent system that leverages multiple MCP (Model Control Protocol) servers to provide a wide range of capabilities, from basic mathematical operations to advanced external service integrations like Google Workspace and web scraping. The agent includes a Telegram bot interface and Server-Sent Events (SSE) for real-time communication.

🌟 Features

- Multi-MCP Architecture: Utilizes multiple MCP servers for distributed processing and diverse capabilities
- Cognitive Modules: Implements perception, decision-making, memory, and action modules
- External Service Integration:
- Google Workspace (Gmail, Google Drive, Google Sheets)
- Web scraping and content extraction
- DuckDuckGo search integration
- Real-time Communication:
- Telegram Bot interface
- Server-Sent Events (SSE) for live updates
- Core Components:
- Agent loop management
- Session handling
- Context management
- Strategic decision making

🏗️ Project Structure

├── agent.py              # Main agent entry point
├── core/                 # Core agent components
│   ├── context.py        # Context management
│   ├── loop.py           # Main agent loop
│   ├── session.py        # Session handling
│   └── strategy.py       # Strategic decision making
├── modules/              # Cognitive modules
│   ├── action.py         # Action execution
│   ├── decision.py       # Decision making
│   ├── memory.py         # Memory management
│   ├── model_manager.py  # Model management
│   ├── perception.py     # Input processing
│   └── tools.py          # Tool definitions
├── config/               # Configuration files
│   ├── models.json       # Model configurations
│   └── profiles.yaml     # MCP server profiles
└── mcp_server_*.py       # MCP server implementations

🚀 Getting Started

Prerequisites

- Python 3.11+
- UV package manager
- Telegram Bot Token (for bot functionality)
- Google Cloud credentials (for Google Workspace integration)

Installation

1. Clone the repository:

git clone <repository-url>

cd <repository-name>

2. Create and activate a virtual environment:

uv venv

venv\Scripts\activate  # On Mac: source venv/bin/activate

3. Install dependencies using UV:

uv sync

4. Set up environment variables:
- Create .env with Gemini API key and Telegram Bot token.
- Generate credentials.json using Google OAuth client.

Configuration

1. Configure MCP servers in config/profiles.yaml
2. Set up model configurations in config/models.json
3. Configure Google Cloud credentials:
- Place credentials.json in the root directory
- Run the application once to generate token.json

🎮 Usage

Starting the Agent

uv run agent.py

Starting the Telegram Bot Server

uv run telegram_sse_server.py

🛠️ MCP Servers

MCP Server 1: Basic Operations

- Mathematical operations - Image processing - File operations

MCP Server 2: Document Processing

- Document indexing - Semantic search - Content extraction - Image captioning

MCP Server 3: Web Integration

- DuckDuckGo search - Web content fetching - Rate-limited requests

MCP Server 4: Google Workspace

- Gmail integration - Google Sheets operations - Google Drive management - F1 standings fetcher (URL scraper)

📡 Communication

Telegram Bot

- Command handling - Message processing - Real-time responses

SSE Server

- Real-time event streaming - Client connection management - Event broadcasting

🧠 Cognitive Architecture

The agent implements a cognitive architecture with the following modules:

- Perception: Processes input and extracts relevant information
- Memory: Manages state and historical data
- Decision: Makes strategic decisions based on input and context
- Action: Executes decided actions through appropriate tools

📝 License

MIT License

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Multi-MCP AI Agent

🌟 Features

🏗️ Project Structure

🚀 Getting Started

Prerequisites

Installation

Configuration

🎮 Usage

Starting the Agent

Starting the Telegram Bot Server

🛠️ MCP Servers

MCP Server 1: Basic Operations

MCP Server 2: Document Processing

MCP Server 3: Web Integration

MCP Server 4: Google Workspace

📡 Communication

Telegram Bot

SSE Server

🧠 Cognitive Architecture

📝 License

Install

More like this

Context 7

1Panel

🔎 GPT Researcher

Serena

FastMCP v2 🚀

MaxKB