Open-source MCP server for Kalshi Trade API v2 market research and trading
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"kalshi-degen-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Kalshi MCP Server An open-source [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for Kalshi’s Trade API v2. It gives MCP clients a practical interface for researching markets, reading an account, and managing orders with RSA-PSS or Ed25519 authentication. > **Important:** This server can place and cancel real orders. It defaults to Kalshi’s **production** environment; set `KALSHI_ENV=demo` explicitly for demo trading. Review the code, configure conservative limits, and test with demo credentials before using production credentials. ## What it provides ### Market research - Exchange status - Markets and events - Individual market data - Order books - Public trades ### Account and trading - Balance, positions, and orders - Current V2 order placement - Batched order placement - Individual and bulk cancellation - Order amendment and quantity reduction - Order-group creation, limits, reset, trigger, listing, and deletion - Legacy order helpers retained for compatibility The `kalshi_endpoint` tool also exposes the validated operations from the bundled Kalshi OpenAPI catalog. It checks the HTTP method, endpoint template, query parameters, request body, and authentication requirements before making a request. ## Requirements - Python 3.11 or newer - A Kalshi API key and Ed25519 private key - An MCP-compatible client ## Installation From a released package or a source checkout: ```bash python -m venv .venv . .venv/bin/activate python -m pip install -e . ``` For environments where `cryptography` must use prebuilt wheels: ```bash python -m pip install --only-binary=:all: httpx cryptography mcp ``` ## Configuration Copy the example configuration and provide credentials through your secret manager or process environment: ```bash cp .env.example .env ``` Required for authenticated tools: ```text KALSHI_API_KEY_ID=your-api-key-id KALSHI_PRIVATE_KEY_BASE64=base64-encoded-PEM-private-key ``` Environment selection is explicit. Productio…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.