Kalshi Kernel MCP server

Kalshi Kernel

An unofficial, safety-focused Model Context Protocol (MCP) server for Kalshi event contracts and perpetual markets. This is a pre-release project that is not ready for trading. The server is designed for agent harnesses such as Hermes and exposes a deliberately small tool surface generated from Kalshi's published API contracts.

Canonical publisher: CopyleftDev. Planned source and container releases use github.com/copyleftdev/kalshi-kernel and ghcr.io/copyleftdev/kalshi-kernel respectively.

[!CAUTION]

Pre-release software that can submit real orders. Published tags are

conformance-tested scaffolds; the current main branch adds market-data,

paper-trading, and live event-contract adapters. Configured live mode can

place, amend, and cancel real orders. Review the exact

commit, configuration, tests, and limits before running it with credentials;

do not infer readiness from the version string.

[!IMPORTANT]

This community project is not an official Kalshi product and is not affiliated

with, endorsed by, sponsored by, or supported by KalshiEX LLC or its

affiliates. “Kalshi” is used only to identify interoperability with Kalshi's

published APIs.

The independent Kernel mark follows a conservative interpretation of Kalshi's published color, contrast, clear-space, and misuse guidance. It does not use or modify Kalshi's logo. See the visual identity usage rules.

Why this project exists

Trading APIs are broad and optimized for application developers. Agents need a narrower boundary with explicit intent, strict schemas, predictable errors, and strong separation between simulation and real-money execution. Kalshi Kernel provides that boundary while continuously testing its generated clients against the latest upstream contracts.

The design priorities are:

• paper mode by default;
• immutable execution mode for the lifetime of a process;
• explicit acknowledgement and credentials before live mode can arm;
• fixed-point strings for prices and quantities;
• strict, generated tool schemas with safety annotations;
• fail-closed behavior when a capability is unavailable;
• traceable alignment with exact OpenAPI operations and AsyncAPI channels; and
• repeatable MCP protocol, race, fuzz, and upstream-drift testing.

Current status

The table describes the current main branch, not the published v0.1.1 tag. The additions are unreleased and the version metadata has not yet advanced.

Shortened. The full README is on GitHub.