Mmcp.market

Kalshi Prediction Markets MCP server

by cejor6·io.github.cejor6/kalshi-mcp-server·v0.1.8
No reviews yet

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

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

3 stars266 downloads/wk

Reviews

Write one

Nobody has reviewed Kalshi Prediction Markets yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Kalshi Prediction Markets tools (27, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • kalshi_cancel_orderwrite action

    Cancel a resting order.

  • kalshi_confirm_orderwrite action

    Execute a previously prepared order.

  • kalshi_decrease_orderwrite action

    Reduce the contract count on a resting order.

  • kalshi_get_api_limits

    Get your account's current API rate-limit tier and remaining headroom.

  • kalshi_get_balance

    Get the current cash balance and unrealized P&L.

  • kalshi_get_environment

    Show which Kalshi environment this MCP server is connected to.

  • kalshi_get_event

    Fetch an event and (optionally) all markets nested under it.

  • kalshi_get_event_candlesticks

    Get OHLC candles per market in an event over a time window.

  • kalshi_get_events

    List events with optional filters.

  • kalshi_get_exchange_schedule

    Get the daily/weekly trading hours schedule for the exchange.

  • kalshi_get_exchange_status

    Get current Kalshi exchange status (open/closed, trading hours).

  • kalshi_get_fills

    List your fills (executions against your orders).

  • kalshi_get_live_orderbook

    Open a WebSocket, subscribe to orderbook updates for a market, collect messages for `duration_s` seconds, and return the latest snapshot plus a count of deltas observed.

  • kalshi_get_market

    Fetch a single market by ticker.

  • kalshi_get_market_candlesticks

    Get OHLC candles for a single market over a time window.

  • kalshi_get_market_trades

    List public trades for a single market.

  • kalshi_get_markets

    List Kalshi markets with optional filters.

  • kalshi_get_orderwrite action

    Get the current state of a single order by id.

  • kalshi_get_orderbook

    Get the current orderbook for a market.

  • kalshi_get_orders

    List your orders (open, filled, cancelled, etc.).

  • kalshi_get_positions

    List your positions.

  • kalshi_get_series

    Fetch a single series by ticker.

  • kalshi_get_settlements

    List markets that have settled and the P&L impact on your account.

  • kalshi_get_trades

    List recent public trades (everyone's, not your own).

  • kalshi_prepare_orderwrite action

    Prepare an order for review. Does NOT send it to Kalshi yet.

  • kalshi_sample_trades

    Listen on the public `trade` channel for a short window and return the trades that occurred.

  • register_all_tools

    Register every tool module against the FastMCP server.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan25 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 7 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Kalshi Prediction Markets repository's README, as published. We do not edit it. Read it on GitHub

kalshi-mcp-server

<!-- mcp-name: io.github.cejor6/kalshi-mcp-server -->

📦 PyPI &nbsp;·&nbsp; 🗂️ MCP Registry &nbsp;·&nbsp; 🐳 Container image &nbsp;·&nbsp; 🚀 Deploy guide

A Model Context Protocol server for Kalshi prediction markets. Native RSA-PSS auth, async token-bucket rate limiting, two-step prepare/confirm order flow with safety caps, optional bundled OAuth proxy for remote-MCP deployments, 26 tools + 4 resources across REST and WebSocket. MIT, designed to be forked.

Works with any MCP client — locally via stdio (Claude Desktop, Claude Code, Cursor, Zed, Continue, Cline, Goose, etc.) or remotely as a self-hosted HTTP server (claude.ai custom connectors today, any OAuth-capable MCP client in the future).

⚠️ **This software lets an LLM place trades. Read DISCLAIMER.md

before deploying.** Trading prediction markets involves substantial

risk of loss. AI agents make mistakes — sometimes confidently. The

authors are not liable for any losses. Test in demo (KALSHI_ENV=demo,

KALSHITRADINGENABLED=0) until you understand the failure modes.

Status — alpha. Auth (REST + WS), rate limiting, safety controls,

26 tools across REST + live channels, and 4 resources are in place.

A long-lived multiplexed WebSocket session and kalshi://markets/{ticker}/orderbook

live resource are planned for v0.2.

Quickstart (30 seconds)

Read-only against Kalshi's demo environment — no real money, no trading flag. This is the safe way to try it.

pipx install kalshi-mcp-server        # or: pip install kalshi-mcp-server

Point any MCP client at it (this is the Claude Desktop / Claude Code shape — see the full client matrix for others):

{
  "mcpServers": {
    "kalshi": {
      "command": "kalshi-mcp",
      "args": ["--env-file", "/Users/you/.kalshi/.env"]
    }
  }
}

Minimal ~/.kalshi/.env (get a demo key at demo.kalshi.co — it's shown once):

KALSHI_API_KEY_ID=<your-demo-key-id>
KALSHI_PRIVATE_KEY_PATH=/absolute/path/to/demo_private_key.pem
KALSHI_ENV=demo

Restart the client and ask it to run a Kalshi tool. Enabling prod and trading is a deliberate opt-in — a few more flags (KALSHIALLOWPROD=1, KALSHITRADINGENABLED=1) — see Configure and the safety model.

What a call looks like

Ask the agent for tradeable markets and kalshifindliquid_markets returns a volume-ranked, combo-excluded shortlist (trimmed, illustrative):

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add kalshi-mcp-server -- uvx kalshi-mcp-server
Add to Cursor

Kalshi Prediction Markets: common questions

Is Kalshi Prediction Markets MCP server safe?
Mostly: it is graded B (83/100). Read the Kalshi Prediction Markets safety report
How do I install Kalshi Prediction Markets?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Kalshi Prediction Markets need an API key?
Yes. The registry entry asks for KALSHI_PRIVATE_KEY_PEM.
Is Kalshi Prediction Markets maintained?
The last commit was 7 days ago (2026-09-20). The latest release is v0.1.8.
What can I use instead of Kalshi Prediction Markets?
Servers from other publishers that do the same job: Ticket Demo MCP server, MCP Server and MCP Server. Compare all Kalshi Prediction Markets alternatives.

Alternatives to Kalshi Prediction Markets

Same job from other publishers: the closest match first, then the best rated.

All Kalshi Prediction Markets alternatives →
  • Ticket Demo
    MCP server demo — tickets, schema discovery, auth, and PII gating. stdio + HTTP.
    B
  • MCP Server
    天启至数 ApocData - MCP Server for A-share market data (46 free, no-auth endpoints)
    A
  • MCP Server
    天启至数 ApocData - MCP Server for A-share market data (46 free, no-auth endpoints)
    A
  • Rede
    MCP server for Rede — Itaú-owned BR acquirer: authorize/capture/refund, zero-auth, card tokens
    More from codespar →
    B
  • spintax.net MCP server
    Write, validate, render and analyze spintax templates. Backed by @spintax/core. No auth.
    A
Kalshi Prediction Markets vs Ticket DemoKalshi Prediction Markets vs MCP ServerKalshi Prediction Markets vs MCP Server

More from cejor6 →