kalshi

kalshi

Enables AI agents to read Kalshi prediction market data, manage portfolios, and place or cancel trades only with explicit user approval.

Category
访问服务器

README

Kalshi Prediction Markets Plugin for Cursor

A Cursor marketplace plugin that connects to the Kalshi prediction markets API, enabling AI agents to read markets and place trades with user approval.

Features

  • Read Market Data: Browse markets, check prices, view orderbooks
  • Portfolio Management: Check balance and view positions
  • Order Placement: Place and cancel orders (only with explicit user approval)
  • Demo & Production: Supports both demo and production environments
  • Secure Authentication: RSA-PSS signature-based authentication

Installation

1. Create API Keys

Visit https://kalshi.com/account/profile and:

  1. Click "Create New API Key"
  2. Save your Key ID (KALSHI_ACCESS_KEY)
  3. Download and save your Private Key (KALSHI_PRIVATE_KEY) - you won't be able to retrieve it again!

For testing, you can also create keys on the demo environment at https://demo.kalshi.com/account/profile.

2. Install the Plugin

  1. Open Cursor
  2. Go to Settings → Plugins → Marketplace
  3. Search for "kalshi"
  4. Click Install

Or clone this repository and install locally:

git clone https://github.com/evanparrott/kalshi

3. Configure Variables

In Cursor, go to Settings → Plugins → kalshi and set:

  • KALSHI_ACCESS_KEY: Your API Key ID from Kalshi
  • KALSHI_PRIVATE_KEY: Your RSA private key (entire PEM file contents)
  • KALSHI_BASE_URL (optional):
    • Production: https://external-api.kalshi.com (default)
    • Demo: https://external-api.demo.kalshi.co

Available Tools

Read-Only Tools (Safe)

  • kalshi_get_balance - Check account balance and portfolio value
  • kalshi_list_markets - Browse available prediction markets
  • kalshi_get_market - Get details about a specific market
  • kalshi_get_orderbook - View current orderbook with prices
  • kalshi_get_positions - View your current positions
  • kalshi_list_orders - View your current orders

Write Tools (Require User Approval)

  • kalshi_create_order - Place a new order
  • kalshi_cancel_order - Cancel an existing order

Usage Examples

Browse Markets

"What prediction markets are available on Kalshi?"

Check Balance

"What's my Kalshi account balance?"

Get Market Info

"Show me details about the market HIGHNY-24JAN01-T60"

Place an Order (Requires Confirmation)

"Buy 10 YES contracts on HIGHNY-24JAN01-T60 at 56 cents"

The agent will:

  1. Show you the market details
  2. Display the current orderbook
  3. Ask for your explicit confirmation
  4. Only then place the order

Safety Features

  • Skill File: The plugin includes a skill file that agents must read before trading
  • Explicit Approval Required: Orders are never placed without user confirmation
  • No Price Guessing: Agents must use actual orderbook prices
  • Clear Confirmations: All trade parameters are confirmed before execution
  • Demo Mode: Test safely with fake money on the demo environment

Demo vs Production

Demo Environment

  • Base URL: https://external-api.demo.kalshi.co
  • Uses fake money for testing
  • Separate account and API keys
  • Perfect for testing the plugin

Production Environment

  • Base URL: https://external-api.kalshi.com
  • Uses real money
  • Default if KALSHI_BASE_URL is not set

Always test with demo first!

Development

Prerequisites

  • Node.js 18 or higher
  • npm

Local Development

# Clone the repository
git clone https://github.com/evanparrott/kalshi
cd kalshi

# Install dependencies
npm install

# Set environment variables
export KALSHI_ACCESS_KEY="your-key-id"
export KALSHI_PRIVATE_KEY="$(cat path/to/your/private-key.pem)"
export KALSHI_BASE_URL="https://external-api.demo.kalshi.co"

# Run the server
npm start

Testing

The MCP server communicates via stdio. You can test it with the MCP Inspector or integrate it directly into Cursor.

Publishing to Cursor Marketplace

This plugin is designed to be submitted to the Cursor marketplace:

  1. Ensure all requirements are met:

    • Public GitHub repository
    • Valid .cursor-plugin/plugin.json
    • Valid .cursor-plugin/mcp.json
    • Skill file at skills/kalshi-trading/SKILL.md
    • Working MCP server
    • No secrets in the repository
  2. Submit at: https://cursor.com/marketplace/publish

  3. Provide:

    • Repository URL
    • Plugin description
    • Usage examples
    • Any special installation notes

API Reference

For full Kalshi API documentation, visit:

Security Notes

  • Never commit your API keys or private key to version control
  • Store private keys securely
  • Use demo environment for testing
  • Private keys cannot be recovered - save them immediately when generated
  • The plugin uses RSA-PSS SHA256 signatures for authentication

Troubleshooting

"Failed to parse KALSHI_PRIVATE_KEY"

Ensure your private key is in PEM format and includes the full key with headers:

-----BEGIN PRIVATE KEY-----
...
-----END PRIVATE KEY-----

"Unauthorized" errors

  • Verify your KALSHI_ACCESS_KEY is correct
  • Ensure KALSHI_PRIVATE_KEY matches the key for your KALSHI_ACCESS_KEY
  • Check you're using the right base URL (demo vs production)

"Market not found" errors

  • Verify the ticker symbol is correct
  • Check the market status with kalshi_get_market
  • Markets may be closed or settled

License

MIT License - see LICENSE file for details.

Author

Evan Parrott

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Disclaimer

This is an unofficial plugin. Use at your own risk. Trading prediction markets involves financial risk. Always understand what you're trading and never trade more than you can afford to lose.

Links

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选