LLM-ready API
Model Context Protocol (MCP)

LLM-Ready API MCP Servers

Overview

There are two options for utilizing the Kensho LLM-Ready API MCP server:

  1. Connecting to the Kensho-hosted remote MCP server
  2. Running the MCP server locally on your machine.

This page will cover instructions for each option.

Important note

For recurring users, make sure to click the 'Connect' button and verify the connection is active.

Connect button

Remote MCP Server

Adding the remote MCP server to Claude

Below are the steps required to add the LLM-Ready API remote MCP server to Claude (opens in a new tab) or Claude Desktop (opens in a new tab).

Important note

You must be a Claude team owner for your organization to add a new connector.

These instructions apply to team owners adding a connector to their team's account for the first time.

  1. Open the “Search and tools” menu on the Claude Desktop homepage in the chat box.
Search and tools
  1. Click “Add connectors”.
Add connectors
  1. Select the “S&P Global” connector and click connect. This will bring you to an Okta browser login flow.
S&P Global connector
  1. Log in with your Kensho Okta credentials. This will redirect you back to Claude Desktop.
Okta login flow
  1. The S&P Global connector will be available under "Search and tools", can now be utilized in your chats with Claude.
MCP Tools
  1. Click into the connector and select the MCP tools you would like to use. We recommend to leave all tools on unless you want to isolate select tools.
Tool selection

Local MCP Server

Overview

This guide covers the steps required to run the Kensho 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

For users who do not already have Python>=3.10 installed, please follow instructions here (opens in a new tab) to get set up.

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

Then confirm in the output that the installation completed successfully.

Adding the local 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. More detailed information can be found on the official MCP documentation (opens in a new tab).

  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> below with your appropriate path which can be found by running which python.
{
  "mcpServers": {
    "kfinance": {
      "command": "<path_to_python>",
        "args": [
          "-m",
          "kfinance.mcp",
          "--stdio"
        ]
     }
   }
}
  1. Exit and restart Claude Desktop.