Skip to main content

A generic multi-tool MCP Agent with Time, Weather, Dictionary, Calculator, etc.

Project description

MCPAgentAI 🚀

PyPI Python Versions License

MCPAgentAI is a standardized tool wrapping framework for implementing and managing diverse tools in a unified way. It is designed to help developers quickly integrate and launch tool-based use cases.

Key Features

  • 🔧 Standardized Wrapping: Provides an abstraction layer for building tools using the MCP protocol.
  • 🚀 Flexible Use Cases: Easily add or remove tools to fit your specific requirements.
  • Out-of-the-Box Tools: Includes pre-built tools for common scenarios:
    • 🕑 Time utilities
    • ☁️ Weather information (API)
    • 📚 Dictionary lookups
    • 🧮 Calculator for mathematical expressions
    • 💵 Currency exchange (API)
    • 📈 Stocks Data: Access real-time and historical stock market information.
    • 🤖 ElizaOS Integration: Seamlessly connect and interact with ElizaOS for enhanced automation.
    • 🐦 Twitter Management: Automate tweeting, replying, and managing Twitter interactions.

Tech Stack 🛠️

  • Python: Core programming language
  • MCP Framework: Communication protocol
  • Docker: Containerization

🤔 What is MCP?

The Model Context Protocol (MCP) is a cutting-edge standard for context sharing and management across AI models and systems. Think of it as the language AI agents use to interact seamlessly. 🧠✨

Here’s why MCP matters:

  • 🧩 Standardization: MCP defines how context can be shared across models, enabling interoperability.
  • Scalability: It’s built to handle large-scale AI systems with high throughput.
  • 🔒 Security: Robust authentication and fine-grained access control.
  • 🌐 Flexibility: Works across diverse systems and AI architectures.

mcp_architecture source

Installation 📦

Install via PyPI

pip install mcpagentai

Usage 💻

Run Locally

mcpagentai --local-timezone "America/New_York"

Run in Docker

  1. Build the Docker image:

    docker build -t mcpagentai .
    
  2. Run the container:

    docker run -i --rm mcpagentai
    

Tutorial: Selecting Specific Tools

You can configure MCPAgentAI to run only certain tools by modifying the agent configuration in your server or by updating the server.py file to only load desired agents. For example:

from mcpagentai.tools.time_agent import TimeAgent
from mcpagentai.tools.weather_agent import WeatherAgent
from mcpagentai.core.multi_tool_agent import MultiToolAgent

multi_tool_agent = MultiToolAgent([
    TimeAgent(),
    WeatherAgent()
])

This setup will only enable Time and Weather tools.


Integration Example: Claude Desktop Configuration

You can integrate MCPAgentAI with Claude Desktop using the following configuration:

claude_desktop_config.json

{
    "mcpServers": {
        "mcpagentai": {
            "command": "docker",
            "args": ["run", "-i", "--rm", "mcpagentai"]
        }
    }
}

Development 🛠️

  1. Clone this repository:

    git clone https://github.com/mcpagents-ai/mcpagentai.git
    cd mcpagentai
    
  2. (Optional) Create a virtual environment:

    python3 -m venv .venv
    source .venv/bin/activate
    
  3. Install dependencies:

    pip install -e .
    
  4. Build the package:

    python -m build
    
  5. Run tests:

    pytest
    

Contributing 🤝

We welcome contributions! Please open an issue or pull request.


License: MIT
Enjoy! 🎉

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcpagentai-0.4.0.tar.gz (33.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcpagentai-0.4.0-py3-none-any.whl (25.9 kB view details)

Uploaded Python 3

File details

Details for the file mcpagentai-0.4.0.tar.gz.

File metadata

  • Download URL: mcpagentai-0.4.0.tar.gz
  • Upload date:
  • Size: 33.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.13.1

File hashes

Hashes for mcpagentai-0.4.0.tar.gz
Algorithm Hash digest
SHA256 d4018bd31c5a2364d452d4844bb419458ab8944150968b1c4c645ca2eaa78ff0
MD5 16dc21bdbe11794db6dc2fe3d325ad81
BLAKE2b-256 4cf194a3f97bd1651807d82b0d956246c11132799d0cc1c629a6343ffcce4a00

See more details on using hashes here.

File details

Details for the file mcpagentai-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: mcpagentai-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 25.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.13.1

File hashes

Hashes for mcpagentai-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8a98c435b3bc52aaf85e152f3517a7ac48ae8752a3652830cedb4f15bb5c305a
MD5 b6f0808391e6b40c7b3416ad41516b8e
BLAKE2b-256 b77dfe5e7f7f8f91b1f90680c316f9c23d005ef3ab3977788c7a7f62415538e6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page