Kalshi Eye

io.github.KalshiEyePublished by GitHub account KalshiEyev0.2.2Updated Oct 29, 2026

Search Kalshi, Polymarket and Limitless markets, order book history, coverage and data files.

VerifiedSTDIODesktop onlyFinanceData & Analytics

Overview

AI-generated overview

Searches the Kalshi Eye archive of Kalshi, Polymarket and Limitless prediction markets, price history and order book data files.

What you can do
  • Search series, events and markets by keyword, venue, category or status
  • Read a series or a single market's terms, status, result and recorded coverage
  • Show a market's recorded YES bid/ask price path
  • Browse datasets, their series and daily Parquet files, and get signed download links
  • Check whether recording is running and how complete recent days were
When to use it
Useful when you want an assistant to look up prediction market questions, compare venues, review how a market's price moved, or find and download historical order book datasets from Kalshi Eye.
Requirements
Runs locally over stdio via uvx (or pip install kalshieye-mcp), so Python and uv are needed. Requires a Kalshi Eye API key in the KALSHIEYE_API_KEY environment variable; a free account works. Network access to kalshieye.com, which KALSHIEYE_BASE_URL can override.
Before you install
Every tool needs the KALSHIEYE_API_KEY secret, which is passed in the client config. Download links count toward a monthly allowance and only cover datasets included in your plan. The server is read-only but sends queries to a third-party service and is independent of the venues it covers.

Installation

In SourceWeft

  1. Open Kalshi Eye in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Kalshi Eye MCP server

An MCP server that lets AI assistants such as Claude and Cursor search the Kalshi Eye archive of prediction market data. It can find Kalshi, Polymarket and Limitless markets, show how a market's price moved, check what was recorded, and list the order book files you can download.

It needs a Kalshi Eye API key: create one at API keys (a free account works) and set it as KALSHIEYE_API_KEY.

Install

Claude Code:

bash
claude mcp add kalshieye -e KALSHIEYE_API_KEY=clab_your_key -- uvx kalshieye-mcp

Claude Desktop, Cursor and other clients (claude_desktop_config.json, .cursor/mcp.json, ...):

json
{  "mcpServers": {    "kalshieye": {      "command": "uvx",      "args": ["kalshieye-mcp"],      "env": { "KALSHIEYE_API_KEY": "clab_your_key" }    }  }}

Without a key, or with a placeholder, every tool answers with how to get one. Listing files and download links cover the datasets your plan includes.

uvx comes with uv. With pip instead: pip install kalshieye-mcp, then use kalshieye-mcp as the command.

Tools

ToolWhat it does
searchFind series, events and markets by keyword, venue, category or status. Series lead and come a page at a time (series_total, has_more, offset); events and markets are the 10 best whose words hold the query, with events_found / markets_found (exact up to 10,000, then *_found_exact: false) and more_events / more_markets, the paged calls that list every match
get_seriesOne series: what it is, how often it runs, markets in the catalog, and days of data files
list_marketsA series' markets, or the markets on every venue holding each word of q (venue narrows it), newest first, with status and result. A page at a time: total (with q, exact up to 10,000, then total_exact: false), and next_cursor (with q) or next_offset, passed back until it is null
list_eventsEvery event on every venue whose title, series name or category holds each word of the query, newest first, a page at a time (next_cursor), with total and total_exact
get_marketOne market's terms, status, result, and how much of it was recorded
market_price_historyThe recorded YES bid/ask path, up to about 240 points over the market's busiest stretch; path_source is life, busiest or window
list_datasetsEvery dataset: what it holds, columns, plan, days available
dataset_seriesWhich series have files in a dataset, with days, rows and size, up to 500 a page with total and next_offset
recording_statusWhether recording is running, and the recorded share of recent days by venue
list_filesDaily Parquet files for a dataset, date range and series, page by page
download_linksSigned download URLs for up to 100 of those files (counts toward the monthly allowance)

Things to ask:

  • "Which bitcoin markets does Kalshi Eye record, and since when?"
  • "What were the last few hours of the Bills vs Rams market on October 12 like?"
  • "How much of the Fed decision series is in the order book files?"
  • "Is the recorder running, and how complete was last week?"

Notes

  • Kalshi is recorded since October 12, 2026; Polymarket, Limitless and Chainlink prices since October 15, 2026. Each UTC day is published the next morning.
  • Prices are dollars between 0 and 1. A Kalshi YES ask is 1 minus the best NO bid. Times are UTC.
  • Free data without any key: a one-day sample on Hugging Face and runnable examples. The Python client for downloading files is kalshieye.
  • KALSHIEYE_BASE_URL points the server at another deployment (default https://kalshieye.com).

Kalshi Eye is independent and is not affiliated with Kalshi, Polymarket or Limitless. MIT licensed.

Source: README.md at commit bb74d1b

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

3
  1. v0.2.2LatestOct 29, 2026
  2. v0.2.1Oct 26, 2026
  3. v0.2.0Oct 25, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts