LLM-ready API
Model Context Protocol (MCP)

MCP Server Setup

Overview

This guide covers the steps required to run the LLM-Ready API MCP (Model Context Protocol) (opens in a new tab) server locally. As there is currently no remote MCP server offering for the LLM-Ready API, users are required to run the MCP server on their own machines.

The guide includes information on ensuring an appropriate Python version is installed, how to install the LLM-Ready API client package, and finally how to connect to the MCP server using Claude Desktop (opens in a new tab).

Python Installation

These instructions are provided for users who do not already have Python >3.10 installed, or are not familiar with Python version management.

  1. Install Pyenv (opens in a new tab): Follow all steps in sections A, B, and C on the Installation section of Pyenv’s documentation (opens in a new tab), using the documentation specific to your operating system.

  2. Install Python >= 3.10: In your terminal or Powershell, run pyenv install 3.10, then run pyenv global 3.10.

  3. Note Python path: Run which python on MacOS/Linux, or (Get-Command cmd).Path on Windows to locate where Python has been installed. This will be important for adding the MCP server to Claude Desktop.

LLM-Ready API Installation

Installation instructions are provided in the kFinance (opens in a new tab) GitHub repo, but for clarity they are reproduced here. Simply run:

pip install kensho-kfinance>=2.6

Then confirm in the output that the installation completed successfully.

Adding the MCP server to Claude Desktop

Below are the basic steps required to add the LLM-Ready API MCP server to Claude Desktop’s available tools.

  1. Open Claude Desktop.
  2. Navigate to the Settings panel.
  3. In the “Developer” tab, click “Edit Config”.
  4. Open claude_desktop_config.json in a text editor like Notepad or TextEdit.
  5. Paste the following settings into the config, replacing /path/to/python with the appropriate path from the “Installing Python” section.
{
  "mcpServers": {
    "kfinance": {
      "command": "/path/to/python",
        "args": [
          "-m",
          "kfinance.mcp",
          "--stdio"
        ]
     }
   }
}
  1. Exit and restart Claude Desktop.