Crosswire MCP Server

Crosswire — MCP server

Pre-trade resolution-risk audit for cross-venue prediction-market arbitrage. Crosswire flags cross-venue resolution mismatches and void risk before execution: void-rule divergence, settlement-scope differences (90-minute vs extra-time), settlement-source and -timing gaps, stale data, and thin liquidity between Polymarket and Kalshi FIFA World Cup 2026 markets — before you execute both legs of a hedge.

It does not predict outcomes and it does not execute trades. It answers one question: if I buy this contract on one venue and sell its twin on the other, do they actually settle on the same thing? When they don't, it names the exact clause that breaks the hedge.

Remote MCP endpoint

https://api.crosswire-api.com/mcp

• Transport: streamable HTTP
• The MCP tools are free — no API key, no signup
• Website: crosswire-api.com · Status & track record: api.crosswire-api.com

Connect

Generic MCP client config (mcp.json):

{
  "mcpServers": {
    "crosswire": {
      "url": "https://api.crosswire-api.com/mcp"
    }
  }
}

Claude Code:

claude mcp add --transport http crosswire https://api.crosswire-api.com/mcp

Tools

check_resolution_risk

Pre-trade safety check for a cross-venue pair. Returns a machine-readable verdict — execution_verdict: safe / caution / block — inside a full Fungibility & Settlement Audit Object (FSAO) with structured findings, top-level divergence flags, venue rule overrides, fee-adjusted spread, and verdict reasons.

Identify the pair by either:

1. canonical_event_id — a pair id from list_covered_events, e.g. "wc26:match:MEX-RSA:2026-06-11:result#home" (#home / #draw / #away selects the outcome leg), or
2. market_a + market_b — one Polymarket conditionId (0x… hex) and one Kalshi ticker (e.g. KXWCGAME-26JUN11MEXRSA-MEX), order-insensitive. outcome on a ref is optional — matching uses only (venue, market_id).

Optional: notional_usd (enables the thin-liquidity check at your trade size).

If the pair is not covered, the tool returns a non-error coverage reply (covered: false) naming the covered matches and the coverage cutoff instead of an FSAO.

Example — real production audit (World Cup opener, Mexico vs South Africa, home leg):

Request:

{
  "canonical_event_id": "wc26:match:MEX-RSA:2026-06-11:result#home"
}

Response (abridged with …):

{
  "audit_id": "aud_01KTW2Y7S3Q3JFYJK863FJB66X",
  "canonical_event_id": "wc26:match:MEX-RSA:2026-06-11:result#home",
  "leg_a": { "venue": "polymarket", "market_id": "0x4cd77d45…10ff", "outcome": "Yes" },
  "leg_b": { "venue": "kalshi", "market_id": "KXWCGAME-26JUN11MEXRSA-MEX", "outcome": "yes" },
  "matching_confidence": 0.98,
  "semantically_fungible": false,
  "scope_divergence_flag": false,
  "void_rule_divergence_flag": true,
  "settlement_source_divergence_flag": true,
  "settlement_timing_divergence_flag": true,
  "polymarket_rule_override": "If the game is canceled entirely, with no make-up game, this market will resolve \"No\". …",
  "kalshi_rule_override": "If the game is cancelled or rescheduled to over two weeks away, the market will resolve to a fair price …",
  "findings": [
    { "code": "void_rule", "severity": "fatal",
      "detail": "Void conditions differ … A core void asymmetry can void one leg while the other settles.",
      "affects_fungibility": true },
    { "code": "settlement_source", "severity": "warn",
      "detail": "fifa.com (UMA-adjudicated) vs Kalshi internal …" },
    { "code": "settlement_timing", "severity": "warn",
      "detail": "2h statistics fallback vs unspecified …" }
  ],
  "fee_adjusted_true_spread": 0.0009,
  "snapshot_age_seconds": 61,
  "execution_verdict": "block",
  "verdict_reasons": [ "void_rule: Void conditions differ …", "…" ],
  "ruleset_sha": "…"
}

That block is the product working as intended: a canceled match pays the Polymarket leg $0 while Kalshi resolves the same position to "a fair price" — the hedge breaks exactly when you need it.

list_covered_events

Free discovery of everything check_resolution_risk can audit: the covered canonical events, their per-outcome pair ids (…#home / #draw / #away), the Polymarket conditionIds and Kalshi tickers with outcome labels for each pair, match dates, the frozen ruleset_sha pinning the identity graph, the coverage kickoff cutoff, and snapshot freshness. Takes no arguments. Use a returned pair_id (or a pair's two market ids) as input to check_resolution_risk.

Verdict semantics

Every FSAO carries the findings that produced the verdict — the audit is explainable, append-only logged server-side, and reproducible from {ruleset_sha, snapshot_ts, canonical_event_id}.

Coverage

FIFA World Cup 2026 match markets listed on both Polymarket and Kalshi, expanding in batches throughout the tournament. Current coverage is always live — query list_covered_events, or /v1/events and /v1/health on the REST API. Listings here are intentionally coverage-generic; the endpoint is the source of truth.

Pricing & keys

The MCP tools are free at launch — no key. The keyed REST API (POST /v1/audit, same FSAO) issues free opening-weekend keys by mail: nicolasduartejaraba@gmail.com.

What we never do

• No outcome prediction. No model probabilities are exposed.
• No execution. No order routing or placement. The gate returns a verdict; your stack decides.
• No custody. No customer keys, funds, or settlement.
• No strategy harvesting. The API sees only the two market references being audited and an optional notional.

Crosswire is an advisory data service. Nothing it returns is financial advice.

License

MIT — covers this repository (listing metadata and documentation). The Crosswire service itself is proprietary.