mcpField
0
0xMONK MCP Server

0xMONK MCP Server

Local
github.com/fere-aiFinance0Updated 79w ago

About 0xMONK MCP Server

0xMONK MCP Server gives AI assistants access to the 0xMONK Trading Agent API for managing trading agents and their activity. Its tools cover agent administration, orders, portfolio monitoring, and market information.

Key features

  1. 01Create, update, and delete trading agents
  2. 02Place token buy and sell orders
  3. 03View portfolios and trade history
  4. 04Query market information and crypto prices
  5. 05Monitor tasks and synchronize on-chain state

Use cases

  1. 01Manage trading agents and inheritance relationships
  2. 02Place token trades and request buy recommendations
  3. 03Review agent holdings, wallets, and trade records
  4. 04Check real-time cryptocurrency market data

MCP support

The MCP server exposes tools for AI assistants to interact with the 0xMONK Trading Agent API, including agent management, trade execution, portfolio monitoring, and market queries.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

0xMONK MCP Server

A Model Conntext Protocol (MCP) server for interacting with the 0xMONK Trading Agent API.

Overview

This project provides a suite of tools for AI assistants to interact with the 0xMONK API, allowing them to manage trading agents, execute trades, and monitor portfolios.

Features

  • Agent Management

    • Create, update, and delete trading agents
    • View agent details and get all available agents
    • Add or remove parent agents (for inheritance)
    • Get agents by user ID or Telegram user ID
  • Trading Operations

    • Execute buy and sell orders for tokens
    • Get buy recommendations for agents
    • Synchronize agent state with blockchain
    • Monitor task status
  • Portfolio Management

    • Monitor agent portfolios, holdings, and trade history
    • Access trading decisions and calls made by agents
    • Get wallet details for agents and Telegram users
  • ProAgent Interaction

    • Query the ProAgent for market information and trading insights
    • Get real-time cryptocurrency prices and market data

Installation

  1. Clone the repository:

    git clone https://github.com/your-username/FereAI-MCP.git
    cd FereAI-MCP
    
  2. Install uv:

    curl -LsSf https://astral.sh/uv/install.sh | sh
    
  3. Create a virtual environment and install dependencies:

    uv venv
    source .venv/bin/activate  # On Windows: .venv\Scripts\activate
    uv pip install -r requirements.txt
    
  4. Configure environment variables:

Get your FereAI Key from https://docs.fereai.xyz/docs/api/api_access and set it in the .env file.

cp .env.example .env
# Edit .env with your configuration

Usage

Run the MCP server:

uv run main.py

Project Structure

FereAI-MCP/
├── .env                  # Environment variables
├── .env.example          # Example environment variables
├── .gitignore            # Git ignore file
├── main.py               # Server entry point
├── monk.json             # API specification
├── pyproject.toml        # Python project configuration
├── README.md             # This file
├── requirements.txt      # Python dependencies
└── src/                  # Source code
    ├── agent.py          # Agent-related API functions
    ├── config.py         # Configuration module
    ├── main.py           # MCP server implementation
    ├── pro_agent.py      # Pro Agent implementation
    └── utils.py          # Utility functions

API Documentation

For more information about the 0xMONK API, refer to the monk.json file or visit the official documentation.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.