Kalshi runs on your own machine — the client starts it, so there is no endpoint to ping. 87 installs a week from pypi. Last commit 21 Feb 2026.
Search, analyze, and trade Kalshi prediction markets through Claude Desktop
What the code does
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
result = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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.
claude mcp add kalshi -e 'KALSHI_API_KEY=<KALSHI_API_KEY>' -e 'KALSHI_PRIVATE_KEY_PATH=<KALSHI_PRIVATE_KEY_PATH>' -- uvx kalshi-mcp{
"mcpServers": {
"kalshi": {
"command": "uvx",
"args": [
"kalshi-mcp"
],
"env": {
"KALSHI_API_KEY": "<KALSHI_API_KEY>",
"KALSHI_PRIVATE_KEY_PATH": "<KALSHI_PRIVATE_KEY_PATH>"
}
}
}
}[mcp_servers.kalshi]
command = "uvx"
args = ["kalshi-mcp"]
env = { KALSHI_API_KEY = "<KALSHI_API_KEY>", KALSHI_PRIVATE_KEY_PATH = "<KALSHI_PRIVATE_KEY_PATH>" }{
"mcpServers": {
"kalshi": {
"command": "uvx",
"args": [
"kalshi-mcp"
],
"env": {
"KALSHI_API_KEY": "<KALSHI_API_KEY>",
"KALSHI_PRIVATE_KEY_PATH": "<KALSHI_PRIVATE_KEY_PATH>"
}
}
}
}{
"servers": {
"kalshi": {
"type": "stdio",
"command": "uvx",
"args": [
"kalshi-mcp"
],
"env": {
"KALSHI_API_KEY": "<KALSHI_API_KEY>",
"KALSHI_PRIVATE_KEY_PATH": "<KALSHI_PRIVATE_KEY_PATH>"
}
}
}
}Put your own values in place of
<KALSHI_API_KEY> (Your Kalshi API key ID), <KALSHI_PRIVATE_KEY_PATH> (Path to your Kalshi RSA private key file (.pem)).
The author’s registry entry marks them as required.
Alternatives to Kalshi
same job, measured the same wayMCP server for end-to-end trading on Kalshi prediction markets: discover, research, trade.
Search, read, bet on, create, and resolve prediction markets on Manifold.
Trade prediction markets with AI agents — skill discovery, autoresearch, and execution.
Search prediction markets, preview trades, and place explicitly confirmed Pariflow orders.
Sourced market and compliance research for Claude Desktop, Claude Code and Cursor.
Research Polymarket and Kalshi markets, traders, signals, backtests, and paper orders.
Sealed prediction-market verdicts, graded in public across Polymarket and Kalshi. No auth required.
Self-hosted MCP server for Kalshi prediction market trading via DFlow on Solana
Kalshi — questions
Answers built from our own checks of this server.