# Kalshi Eye (pypi · kalshieye-mcp)

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

- Trust score: 81/100 (high trust)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `kalshieye-mcp`: 81/100 (this document), [markdown](https://verifymcp.io/servers/kalshieye-kalshieye-mcp/kalshieye-mcp.md), [page](https://verifymcp.io/servers/kalshieye-kalshieye-mcp/kalshieye-mcp)

## Channel facts

- Registry: `pypi`
- Package: `kalshieye-mcp`
- Version: `0.2.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 1 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to KalshiEye/kalshieye-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1468 tokens (~133/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Kalshi Eye MCP server?

Kalshi Eye runs locally as a PyPI package, launched with uvx kalshieye-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add kalshieye-kalshieye-mcp -- uvx kalshieye-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "kalshieye-kalshieye-mcp": {
      "command": "uvx",
      "args": [
        "kalshieye-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "kalshieye-kalshieye-mcp": {
      "command": "uvx",
      "args": [
        "kalshieye-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add kalshieye-kalshieye-mcp -- uvx kalshieye-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kalshieye-kalshieye-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "kalshieye-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add kalshieye-kalshieye-mcp --command uvx --arg kalshieye-mcp
```

### Hermes

```yaml
mcp_servers:
  kalshieye-kalshieye-mcp:
    command: "uvx"
    args: ["kalshieye-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "kalshieye-kalshieye-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "kalshieye-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add kalshieye-kalshieye-mcp -t stdio -c uvx -a kalshieye-mcp
```

### Other

```json
{
  "mcpServers": {
    "kalshieye-kalshieye-mcp": {
      "command": "uvx",
      "args": [
        "kalshieye-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 79, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-28 (score 63, 0)

- [functional regression] Schema quality: pass → fail
- [functional] Package version: 0.2.1 → 0.2.2

### 2026-10-26 (score 63, +1)

- [functional improvement] Stability: unverified → 0.07
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-10-24 (score 62)

First indexed and scored.

## MCP tools (11)

### `search` (~297 tokens)

Search Kalshi, Polymarket and Limitless series, events and markets by keyword.

Examples: "bitcoin 15 minute", "fed rate", "NFL", "New York temperature".
category is an archive category such as Crypto, Economics, Sports or Politics.
status "live" keeps markets still trading.

series is one page: limit is 1 to 50 series, series_total counts every matching series, and when
has_more is true, call again with offset + limit for the next page.

Series lead: a query naming a series finds it first. events and markets are the 10 best whose own
words (title, ticker, event, category, series name) hold every query word: still trading and
closing soonest first, then the latest closed. They are not all of them: list_events and
list_markets with q (and venue when given) list every match, as more_events / more_markets say.
events_found and markets_found count those lists exactly up to 10,000; past that the count is
10,000 and events_found_exact / markets_found_exact is false (say "10,000+"). All are null when
the query has no word to match (only dates or single letters).

Input parameters:

- `category`
- `limit` (integer)
- `offset` (integer)
- `query` (string, required)
- `status`
- `venue`

### `get_series` (~73 tokens)

One series (for example KXBTC15M, KXFEDDECISION, or a pm:/lm: id from search): what it is, how often it
runs, how many markets the catalog lists, and how many days of data files the archive has for it.

Input parameters:

- `series_id` (string, required)

### `list_markets` (~245 tokens)

Markets a page at a time, newest first, with status, result and times.

With series, one series' markets (q then narrows them by text in the ticker, title or event). With q
and no series, markets on every venue holding each of its whole words in the ticker, series and its
name, title, event or category (venue narrows it to one venue). With neither, every Kalshi market by
close. status is a market status such as active, closed or finalized.

limit is 1 to 200 a page. total counts every match (null only on the plain all-markets list); with q
it is exact up to 10,000, and past that it is 10,000 with total_exact false (say "10,000+"). To get
every market: with q, pass next_cursor back as cursor until it is null; otherwise pass next_offset
back as offset until it is null.

Input parameters:

- `cursor`
- `limit` (integer)
- `offset` (integer)
- `q`
- `series`
- `status`
- `venue`

### `list_events` (~165 tokens)

Every event on every venue whose words (id, title, subtitle, series id and name, category) hold
each word of query, newest close first, a page at a time: what search's more_events lists.

status is live, closed or settled. limit is 1 to 200 a page. total is exact up to 10,000, and past
that it is 10,000 with total_exact false (say "10,000+"). Pass next_cursor back as cursor until it
is null to get every event; get_series or list_markets(series=...) open one.

Input parameters:

- `category`
- `cursor`
- `limit` (integer)
- `query` (string, required)
- `status`
- `venue`

### `get_market` (~80 tokens)

One market: terms, status, result, and how much of it the archive recorded.

ticker is a Kalshi market ticker (KXBTC15M-26OCT121545-45) or a Polymarket or Limitless market id as
search returns it (pm:0x..., lm:...).

Input parameters:

- `ticker` (string, required)

### `market_price_history` (~146 tokens)

The recorded YES best bid and ask path for one market: up to about 240 points over the market's
busiest stretch (its whole life when that is short). path_source says which: "life" or "busiest",
or "window" when the 1-minute bars give no path and the points come from the recorded order book in
the preview's window. The window is the span the points cover.

For every order book change, use the daily Parquet files (list_datasets, list_files). Previews are built
for Kalshi markets; Polymarket and Limitless markets may return no points.

Input parameters:

- `ticker` (string, required)

### `list_datasets` (~56 tokens)

Every dataset in the archive (order books, top of book, minute bars, trades, settlements, Polymarket,
Limitless, Chainlink...): what it holds, the plan it needs, its dates, and its columns.

### `dataset_series` (~92 tokens)

Which series have files in one dataset (for example book_l2 or trades), with days, rows and size.

limit is 1 to 500 series a page and total counts them all. When next_offset is set, call again with
it as offset for the next page.

Input parameters:

- `dataset_id` (string, required)
- `limit` (integer)
- `offset` (integer)
- `query`

### `recording_status` (~33 tokens)

Whether the recorder is running now, the last published day, and the recorded share of recent days,
overall and by venue.

### `list_files` (~84 tokens)

Daily Parquet files for a dataset and date range (YYYY-MM-DD, UTC), optionally one series.
When next_cursor is set, call again with it for the next page.

Input parameters:

- `cursor`
- `dataset` (string, required)
- `end_date` (string, required)
- `limit` (integer)
- `series`
- `start_date` (string, required)

### `download_links` (~46 tokens)

Signed download URLs for up to 100 file keys from list_files.

The first download of a file in a month counts toward the plan's monthly allowance.

Input parameters:

- `keys` (array, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/kalshieye-kalshieye-mcp/kalshieye-mcp#diagnostics

## Score history

- 2026-11-04: 81
- 2026-11-03: 81
- 2026-11-02: 80
- 2026-11-01: 80
- 2026-10-31: 79
- 2026-10-30: 79
- 2026-10-29: 63
- 2026-10-28: 63
- 2026-10-27: 63
- 2026-10-26: 63
- 2026-10-25: 62
- 2026-10-24: 62

## Common questions

### What is the Kalshi Eye MCP server?

Kalshi Eye is an MCP server listed in the public MCP registry as io.github.KalshiEye/kalshieye-mcp. Search Kalshi, Polymarket and Limitless markets, order book history, coverage and data files. This page covers its PyPI package (kalshieye-mcp).

### Is the Kalshi Eye MCP server safe to use?

Kalshi Eye scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Kalshi Eye MCP server expose?

Kalshi Eye exposes 11 tools: search, get_series, list_markets, list_events, get_market, and 6 more. Their descriptions and schemas cost roughly 1,317 tokens of context every time the server is loaded.

### Is the Kalshi Eye MCP server still maintained?

Kalshi Eye is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Kalshi Eye MCP server under?

Kalshi Eye declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/kalshieye-mcp/
- Socket report: https://socket.dev/pypi/package/kalshieye-mcp
- Repository: https://github.com/KalshiEye/kalshieye-mcp
- Website: https://kalshieye.com/
- Changelog RSS feed: https://verifymcp.io/servers/kalshieye-kalshieye-mcp/kalshieye-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/kalshieye-kalshieye-mcp/kalshieye-mcp.json
- HTML version of this page: https://verifymcp.io/servers/kalshieye-kalshieye-mcp/kalshieye-mcp