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.

• 🔧 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:
  • 🐦 Twitter Management: Automate tweeting, replying, and managing Twitter interactions.
  • 💸 Crypto: Get the latest cryptocurrency prices.
  • 🤖 ElizaOS Integration: Seamlessly connect and interact with ElizaOS for enhanced automation.
  • 🕑 Time utilities
  • ☁️ Weather information (API)
  • 📚 Dictionary lookups
  • 🧮 Calculator for mathematical expressions
  • 💵 Currency exchange (API)
  • 📈 Stocks Data: Access real-time and historical stock market information.
  • [WIP] 📰 News: Retrieve the latest news headlines.

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

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.

pip install mcpagentai

mcpagentai --local-timezone "America/New_York"

1. Build the Docker image: docker build -t mcpagentai .

2. Run the container: docker run -i --rm mcpagentai

MCPAgentAI offers robust Twitter integration, allowing you to automate tweeting, replying, and managing Twitter interactions. This section provides detailed instructions on configuring and using the Twitter integration, both via Docker and .env + scripts/run_agent.sh.

When running MCPAgentAI within Docker, it's essential to configure environment variables for Twitter integration. These variables are divided into two categories:

These credentials are used by the Node.js client within the agent for managing Twitter interactions.

ENV TWITTER_USERNAME=
ENV TWITTER_PASSWORD=
ENV TWITTER_EMAIL=

These credentials are utilized by Tweepy for interacting with Twitter's API v2.

ENV TWITTER_API_KEY=
ENV TWITTER_API_SECRET=
ENV TWITTER_ACCESS_TOKEN=
ENV TWITTER_ACCESS_SECRET=
ENV TWITTER_CLIENT_ID=
ENV TWITTER_CLIENT_SECRET=
ENV TWITTER_BEARER_TOKEN=

1. Build the Docker image:

   docker build -t mcpagentai .

2. Run the container:

   docker run -i --rm mcpagentai

Create a .env file in the root directory of your project and add the following environment variables:

ANTHROPIC_API_KEY=your_anthropic_api_key
ELIZA_PATH=/path/to/eliza
TWITTER_USERNAME=your_twitter_username
TWITTER_EMAIL=your_twitter_email
TWITTER_PASSWORD=your_twitter_password
PERSONALITY_CONFIG=/path/to/personality_config.json
RUN_AGENT=True

# Tweepy (Twitter API v2) Credentials
TWITTER_API_KEY=your_twitter_api_key
TWITTER_API_SECRET=your_twitter_api_secret
TWITTER_ACCESS_TOKEN=your_twitter_access_token
TWITTER_ACCESS_SECRET=your_twitter_access_secret
TWITTER_CLIENT_ID=your_twitter_client_id
TWITTER_CLIENT_SECRET=your_twitter_client_secret
TWITTER_BEARER_TOKEN=your_twitter_bearer_token

1. Make the script executable:

   chmod +x scripts/run_agent.sh

2. Run the agent:

   bash scripts/run_agent.sh

You can configure MCPAgentAI to run with Twitter integration either using Docker or by setting up environment variables in a .env file and running the scripts/run_agent.sh script.

This flexibility allows you to choose the method that best fits your deployment environment.

MCPAgentAI offers seamless integration with ElizaOS, providing enhanced automation capabilities through Eliza Agents. There are two primary ways to integrate Eliza Agents:

This approach allows you to use Eliza Agents without running the Eliza Framework in the background. It simplifies the setup by embedding Eliza functionality directly within MCPAgentAI.

Steps:

1. Configure MCPAgentAI to Use Eliza MCP Agent: In your Python code, add Eliza MCP Agent to the MultiToolAgent:

   from mcpagentai.core.multi_tool_agent import MultiToolAgent
   from mcpagentai.tools.eliza_mcp_agent import eliza_mcp_agent
   
   multi_tool_agent = MultiToolAgent([
       # ... other agents
       eliza_mcp_agent
   ])

Advantages:

• Simplified Setup: No need to manage separate background processes.
• Easier Monitoring: All functionalities are encapsulated within MCPAgentAI.
• Highlight Feature: Emphasizes the flexibility of MCPAgentAI in integrating various tools seamlessly.

This method involves running the Eliza Framework as a separate background process alongside MCPAgentAI.

Steps:

1. Start Eliza Framework: bash src/mcpagentai/tools/eliza/scripts/run.sh

2. Monitor Eliza Processes: bash src/mcpagentai/tools/eliza/scripts/monitor.sh

3. Configure MCPAgentAI to Use Eliza Agent: In your Python code, add Eliza Agent to the MultiToolAgent:

   from mcpagentai.core.multi_tool_agent import MultiToolAgent
   from mcpagentai.tools.eliza_agent import eliza_agent
   
   multi_tool_agent = MultiToolAgent([
      # ... other agents
      eliza_agent
   ])

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.

You can integrate MCPAgentAI with Claude Desktop using the following configuration (claude_desktop_config.json), note that local ElizaOS repo is optional arg:

{
    "mcpServers": {
        "mcpagentai": {
            "command": "docker",
            "args": ["run", "-i", "-v", "/path/to/local/eliza:/app/eliza", "--rm", "mcpagentai"]
        }
    }
}

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

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

License: MIT
Enjoy! 🎉