Cover image
Try Now
2025-04-13

A MCP server to interact with Kalshi prediction markets

3 years

Works with Finder

1

Github Watches

0

Github Forks

1

Github Stars

MCP Server Kalshi

This is an MCP server for the Kalshi REST API

Configuration

Claud Desktop

Setting up with UVX
"mcpServers": {
  "kalshi": {
    "command": "uvx",
    "args": ["mcp-server-kalshi"],
    "env": {
        "KALSHI_PRIVATE_KEY_PATH": "PATH TO YOUR RSA KEY FILE",
        "KALSHI_API_KEY": "<YOUR KALSHI API KEY>",
        "BASE_URL": "https://api.elections.kalshi.com"
    }
  }
}
Setting up with Docker
  1. Build the container from root directory docker build -t mcp-server-kalshi .

  2. Configure client to run the container (ensure the bind command gives the container access to your rsa key files)

"mcpServers": {
  "kalshi": {
    "command": "docker",
    "args": ["run", "--rm", "-i", "--mount", "type=bind,src=/Users/username,dst=/Users/username", "-e", "KALSHI_PRIVATE_KEY_PATH", "-e", "KALSHI_API_KEY","-e", "BASE_URL", "mcp-server-kalshi"],
    "env": {
        "KALSHI_PRIVATE_KEY_PATH": "PATH TO YOUR RSA KEY FILE",
        "KALSHI_API_KEY": "<YOUR KALSHI API KEY>",
        "BASE_URL": "https://api.elections.kalshi.com"
    }
  }
}

Local Development

  1. Create a .env file in the root directory with the following variables

    • BASE_URL The kalshi API URL
    • KALSHI_API_KEY The API key for the corresponding environment
    • KALSHI_PRIVATE_KEY_PATH A filepath to a file containing your Kalshi RSA private key
  2. Install deps via uv pip install -e . Dev deps can be installed with uv pip install -e .[dev]

  3. Run with uv run start

Getting Kalshi API Creds

To get Kalshi API creds, follow the instrictions here

Getting a Test Account

You may want to run the server against a kalshi demo account. To get an account, follow the instructions here

Then, set BASE_URL=https://demo-api.kalshi.co for this MCP server and update your KALSHI_API_KEY and KALSHI_PRIVATE_KEY_PATH to point towards credentials generated in the testing environment

UVX

To run in MCP inspector

npx @modelcontextprotocol/inspector uv --directory /path/to/your/mcp-server-kalshi run start

To run in claud desktop, update your MCP config to:

{
    "mcpServers": {
        "kalshi": {
            "command": "uv",
            "args": [ 
            "--directory",
            "/<path to repo root directory>",
            "run",
            "start"
            ],
            "env": {
                "KALSHI_PRIVATE_KEY_PATH": "PATH TO YOUR RSA KEY FILE",
                "KALSHI_API_KEY": "<YOUR KALSHI API KEY>",
                "BASE_URL": "https://api.elections.kalshi.com"
            }
        }
    }
}

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Bora Yalcin
  • Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Lists Tailwind CSS classes in monospaced font

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • Yasir Eryilmaz
  • AI scriptwriting assistant for short, engaging video content.

  • apappascs
  • Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.

  • ShrimpingIt
  • Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx

  • jae-jae
  • MCP server for fetch web page content using Playwright headless browser.

  • HiveNexus
  • An AI chat bot for small and medium-sized teams, supporting models such as Deepseek, Open AI, Claude, and Gemini. 专为中小团队设计的 AI 聊天应用,支持 Deepseek、Open AI、Claude、Gemini 等模型。

  • ravitemer
  • A powerful Neovim plugin for managing MCP (Model Context Protocol) servers

  • patruff
  • Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

    Reviews

    1 (1)
    Avatar
    user_YHkKBB8K
    2025-04-16

    I've been using the QGISMCP - QGIS Model Context Protocol Integration by jjsantos01 and it's been transformative for my GIS projects. The seamless integration with QGIS enhances workflow efficiency and the intuitive interface makes complex data management straightforward. Highly recommend checking it out at https://mcp.so/server/qgis_mcp/jjsantos01!