mcpbeat Sign in

Kalshi Prediction Markets MCP Server

local only

Kalshi Prediction Markets runs on your own machine — the client starts it, so there is no endpoint to ping. 269 installs a week from pypi. Last commit 15 Sep 2026.

MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.

Installs per day peak 500 · avg 109 · -40% w/w
a month agotoday
269
Installs / week
pypi · kalshi-mcp-server
3
Stars
2 open issues
15 Sep 2026
Last commit
0 releases in 90 days
MIT
License
Python

Nothing serious here today

Today is the operative word: we check Kalshi Prediction Markets every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add kalshi-mcp-server -- uvx kalshi-mcp-server
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "kalshi-mcp-server": {
      "args": [
        "kalshi-mcp-server"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.kalshi-mcp-server]
command = "uvx"
args = ["kalshi-mcp-server"]
.cursor/mcp.json
{
  "mcpServers": {
    "kalshi-mcp-server": {
      "args": [
        "kalshi-mcp-server"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "kalshi-mcp-server": {
      "args": [
        "kalshi-mcp-server"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: KALSHI_API_KEY_ID (Kalshi API key ID from https://kalshi.com/account/profile), KALSHI_PRIVATE_KEY_PATH (Filesystem path to the RSA private key PEM. Set this or KALSHI_PRIVATE_KEY_PEM.), KALSHI_PRIVATE_KEY_PEM (Inline PEM contents, for hosted deploys without filesystem access.), KALSHI_ENV (demo or prod. Defaults to demo for safety.), KALSHI_ALLOW_PROD (Must be 1 for the server to start with KALSHI_ENV=prod. Defaults to 0.), KALSHI_TRADING_ENABLED (Must be 1 for order-placement tools to operate. Read-only by default (0).). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Kalshi Prediction Markets

same job, measured the same way
MCP Server Kalshi
by 9crusher

MCP server for end-to-end trading on Kalshi prediction markets: discover, research, trade.

242 installs/wk local only
Limitless MCP Server
by joinquantish

MCP server for Limitless Exchange prediction markets on Base

local only
Kalshi MCP Server
by joinquantish

Self-hosted MCP server for Kalshi prediction market trading via DFlow on Solana

local only
MCP Server Trello
by delorenj

MCP server for Trello boards with rate limiting, type safety, and comprehensive API integration.

1 987 installs/wk local only
Kalshi
by pipeworx-io

Kalshi MCP — US-regulated prediction-market data (no auth on public reads).

42 tools answering
Polymarket MCP Server
by joinquantish

Self-hosted MCP server for AI agent trading on Polymarket prediction markets

local only
Kalshi MCP
by kalshi-mcp

Hosted MCP for Kalshi prediction markets: search, odds, order books, settlement rules, and trading.

answering
Kalshi Kernel
by copyleftdev

Unofficial safety-focused MCP server for Kalshi market data and explicitly authorized trading

local only

Kalshi Prediction Markets — questions

Answers built from our own checks of this server.

Why is there no uptime for Kalshi Prediction Markets?
Kalshi Prediction Markets runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package kalshi-mcp-server was installed 269 times last week.
How do I connect Kalshi Prediction Markets?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls kalshi-mcp-server straight from pypi; nothing to host, nothing to sign up for.
How many people use Kalshi Prediction Markets?
The pypi package kalshi-mcp-server was installed 269 times in the last week. Week over week that is -40%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Kalshi Prediction Markets open source?
Yes — it is published under the MIT licence, written in Python, 3 stars on GitHub and 2 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.