XRPL MCP Server provides a standardized API for AI models to access XRP Ledger data and functionality. It exposes tools that let you fetch account information, trust lines and issued currencies, NFTs owned by an account, transaction history, and order book data from the XRP Ledger DEX, as well as submit signed transactions and query server information. This enables Claude, GPT, or other MCP-compatible assistants to request XRP Ledger data directly through the MCP interface without needing to manage XRP Ledger connectivity themselves. Tools are designed with simple parameters (e.g., address for accounts, limit for result counts, and optional filters) and return JSON-formatted results for easy consumption by LLMs and downstream tooling. The server is designed to be run in a Python environment and can be integrated into MCP-enabled AI pipelines using the standard MCP workflow.

Prerequisites:

• Python 3.8+ installed on your system
• Access to install Python packages (pip)
• Internet connection to download dependencies

Option A: Install from source

1. Clone the repository: git clone https://github.com/lgcarrier/xrpl-mcp-server.git cd xrpl-mcp-server

2. (Optional) Create and activate a virtual environment: python -m venv venv

   macOS/Linux

   source venv/bin/activate

   Windows

   venv\Scripts\activate

3. Install dependencies: pip install -r requirements.txt

4. Run from source: python -m xrpl_mcp_server

Option B: Install as an installed package

1. Install the package from PyPI: pip install xrpl-mcp-server

2. Run the installed package: python -m xrpl_mcp_server

Configuration tip:

• Set XRPL_NODE_URL to point to your XRP Ledger node if you’re not using the default public node. The default is https://s1.ripple.com:51234/.

Notes and tips:

• The default XRP Ledger node URL is XRPL_NODE_URL=https://s1.ripple.com:51234/; override it via environment variable for private or dedicated nodes.
• To use with Claude or other MCP-enabled assistants, ensure you have run the MCP installation command (mcp install xrpl-mcp-server) and that the XRPL MCP server is accessible to the AI environment.
• The server exposes several tools (get_account_info, get_account_lines, get_account_nfts, get_account_transactions, get_server_info, submit_transaction, get_transaction_info, get_book_offers). Each tool expects parameters as described in the README and returns JSON-formatted data.
• When deploying in production, consider securing access to the MCP endpoints and limiting who can invoke sensitive operations like submit_transaction.
• If you need to customize behavior (timeouts, caching, or isolation), extend the server configuration or contribute to the module according to the project’s guidelines.