Advertise
MCP.so
Sign In

MCP Server Kalshi

@9crusher

Repository

Basic information

Category

Other

License

MIT

Transports

stdio

Author

9crusher

About MCP Server Kalshi

A MCP server to interact with Kalshi prediction markets

MCP Server Kalshi config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-kalshi": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "uv",
        "--directory",
        "/path/to/mcp-server-kalshi",
        "run",
        "start"
      ]
    }
  }
}

MCP Server Kalshi tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Server Kalshi?

It is an MCP (Model Context Protocol) server that gives Claude Code and other agent harnesses a first-class interface to Kalshi, the regulated prediction-market exchange. It supports end-to-end trading: browsing markets, researching them, reading settlement rules, pulling contract-terms PDFs, and executing trades through MCP tools.

How to use MCP Server Kalshi?

Configure via environment variables (KALSHI_ENV, KALSHI_API_KEY, KALSHI_PRIVATE_KEY_PATH). Run with uvx mcp-server-kalshi or via Docker. The server targets the Kalshi demo sandbox by default; set KALSHI_ENV=prod for real money. Order-placing tools require confirm=true to execute; without it they only return a preview.

Key features of MCP Server Kalshi

  • Discover markets, events, and series with filtering (no free‑text search).
  • Research markets via orderbook, candlesticks, and trade history.
  • Read full settlement rules and download contract‑terms PDFs.
  • Manage portfolio: balance, positions, fills, settlements.
  • Place, cancel, amend, and decrease orders with a natural buy/sell model.
  • Safety defaults: demo environment, preview‑only orders, optional credentials for read tools.

Use cases of MCP Server Kalshi

  • Let an agent research prediction market rules and settlement conditions before deciding to trade.
  • Automate portfolio monitoring and order adjustments based on market updates.
  • Build a trading assistant that can explain market orderbooks and candlestick data.
  • Enable a voice or chat interface to browse Kalshi markets and execute trades.

Frequently asked questions

1

What environments does MCP Server Kalshi support?

It supports `demo` (sandbox) and `prod` (real money). The default is `demo`.

2

Are API credentials required?

No. All market and rules tools work without authentication. Portfolio and order tools require a Kalshi API key and RSA private key.

3

How does the safety-by‑default feature work?

Order‑placing tools (`create_order`, `amend_order`) require `confirm=true` to actually place an order. Without it they return a human‑readable preview and the exact payload without executing anything.

4

What is the order model used by MCP Server Kalshi?

It exposes a natural model: `action` (buy/sell) + `side` (yes/no) + limit price in whole cents. The server automatically translates the underlying Kalshi API (which quotes everything from the YES leg) including the buy‑NO ⇄ sell‑YES price inversion.

5

What are the runtime dependencies?

Python 3.12 or later. Install dependencies with `uv sync`. For local development, include `--extra dev`.

Comments

More Other MCP servers

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Advertise