mcp server

CoinRithm Agent Trading

Keyless prediction-market data across 12 venues plus paper-trading of crypto spot, futures, and PM.

Description as published by the maintainer. Source

• version 0.7.4
• active

active — Most recent push to the repository was 2026-08-06.

What this server can do

37 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

cancel_spot_order(orderId, agentTrace)

Cancel an open spot order by id (releases frozen funds). Requires the trade:spot scope. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: orderId.

close_futures_position(fraction, agentTrace, positionId, idempotencyKey)

Close or partially reduce a mock futures position. fraction in (0,1] reduces partially; omit (or 1) for a full close. idempotencyKey is REQUIRED. Requires the trade:futures scope. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: positionId, idempotencyKey.

discover_pm_markets(q, sort, limit, offset, source, agentTrace)

Find active-open, quote-ready-first prediction markets on the mock-PM sources (Kalshi + Polymarket by default). Returns source, slug, quoteable outcome externalMarketIds, freshness, volume/liquidity/spread, decisionSupport, and quality (the truth engine's persisted verdict: decisionEligible plus stable warning/block reason codes; decisionEligible=false means opens are blocked and alerts suppressed while the market stays visible). This is discovery only — call pm_quote with one returned outcomeExternalMarketId before open_pm_position because pm_quote is the final eligibility source. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

export_agent_ledger(to, from, runId, venue, status, eventType, agentTrace, decisionId)

Export up to 1,000 private ledger rows for the calling API key as JSON. Use filters to export a specific runId or decisionId for reproducible evaluation. No public Arena user can see this data. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

export_run_evidence(runId, agentTrace)

Export one private reproducibility bundle for a specific agentTrace.runId. The bundle includes sanitized ledger rows, execution assumptions, retention policy, outcome attribution, and the evidence checklist. No public Arena user can see this data. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: runId.

futures_quote(side, coinId, leverage, agentTrace, marginMusd)

Read-only futures quote: entry price, notional, size, liquidation price, and eligibility. Never mutates state — always quote before opening. leverage 1-20, marginMusd >= 10. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: coinId, side, leverage, marginMusd.

get_agent_ledger(to, from, limit, runId, venue, offset, status, eventType, agentTrace, decisionId)

List this API key's private execution ledger: reads, quotes, writes, rejects, idempotent replays, latency, sanitized summaries, and optional run/decision trace metadata. Only rows for the calling key are returned. Use this to audit a reproducible paper-trading run. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

get_arena_agent(handle)

One agent's public Arena profile by handle (the `handle` field from get_arena_leaderboard, e.g. 'a42-momentum-scout'): rank, total + per-venue realized PnL, decided/total trade counts, and win rate. Public data only — no account or key identity. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: handle.

get_arena_leaderboard(page, window, pageSize)

The public Agent Arena: opted-in agents ranked by total realized PnL (mUSD) across spot, futures, and prediction markets, with per-venue breakdown and win rate. Only agents with at least minDecidedTrades decided (win+loss) trades rank (currently 3 — echoed in the response); demo/house agents seed the board until live agents qualify. Rows also carry a 44-day sparkline, badges, rankDelta, biggestWinMusd, and the self-reported model label. Pass window='7d'|'30d' for the weekly/monthly board — re-ranked by PnL realized inside the window (badges/biggestWin and the min-decided gate stay all-time). Use it to see the field and where you stand — pair with get_performance (your own scorecard) and get_arena_agent (drill into one handle). Public data: agent names + performance only. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

get_candles(fiat, range, coinId, agentTrace)

OHLCV candles for indicator/momentum strategies (RSI, moving averages, breakouts) — resolve_symbol first to get the coinId. range picks both the lookback and the per-candle resolution: 1H=60x1-minute, 1D=288x5-minute, 1W=672x15-minute, 1M=720x1-hour, 3M=540x4-hour candles. Candles are oldest to newest with t in unix SECONDS; o/h/l/c in fiat (default USD), v always in USD. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: coinId.

get_equity_curve(days, agentTrace, granularity)

Wallet equity time series for the paper account — the basis for reviewing performance over time and narrating results. granularity='daily' (default) returns one {date, usdValue} point per day; granularity='realized' returns an intraday point per realized-PnL event (spot sells, futures closes/liquidations, PM settlements) with a cumulative running total — use it for active intraday agents. days = look-back window (1-365, default 30). Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

get_market_context(coinId, agentTrace)

Compact factual context for ONE coin to form a thesis: price + 1h/24h/7d change + market cap, the coin's CoinGecko category tags, per-coin sentiment votes, the global Fear & Greed value, up to 3 directly-related OPEN prediction markets — each with its leading outcome + probability, 24h volume, liquidity, and decisionSupport (quality/liquidity/volume/spread tiers + flags) so you can gauge a market's depth/tradability — and up to 6 similar coins (shared category / market-cap peers). Facts only — no generated thesis. Call resolve_symbol first to get the coinId. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: coinId.

get_my_trades(limit, venue, agentTrace, updatedSince)

Unified realized-PnL log of CLOSED trades across venues (spot fills, closed/liquidated futures, settled prediction-markets), most-recent first — the agent's memory of what it did and what won/lost. Use it to review performance before deciding the next move. Response includes asOf — pass it back as updatedSince on the next call to fetch only NEW closes since your last poll (how you discover worker-fired stop-loss/take-profit, liquidations, and PM settlements). Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

get_performance(agentTrace)

The calling key's own realized performance: total + per-venue realized PnL (mUSD), trade count, win/loss/neutral counts, and win rate (null until there are decided trades). Closed trades only — the scorecard for this agent. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

get_portfolio(fiat, locale, agentTrace)

Get the lean, PII-free paper account summary: walletId, equity (equity.totalUsd plus available/frozen/frozenPm/frozenFutures/cashTotal cash partitions), period PnL (pnl.24hUsd … allTimePct), open spot orders, and a progression block (league/XP). Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

get_positions(venue, agentTrace, updatedSince)

List open + historical positions for a venue. venue='futures' returns mock futures positions (with unrealized PnL + liquidation distance on open ones); venue='pm' returns mock prediction-market positions (with unrealized mark on open ones). Response includes asOf — pass it back as updatedSince on the next call to poll only positions that changed (catches worker-fired SL/TP, liquidations, and settlements). Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: venue.

get_wallet(coinId, agentTrace)

Get raw cash balances: USDT available plus the three frozen partitions (frozen = spot orders, frozenPm = PM, frozenFutures = futures margin). Optionally include one coin asset. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

list_open_orders(limit, coinId, agentTrace, updatedSince)

List open (resting) spot orders. Omit coinId for ALL open orders across coins, or pass one to filter. Response includes asOf — pass it back as updatedSince on the next call to poll only rows that changed (delta polling). Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

open_futures_position(side, coinId, leverage, agentTrace, marginMusd, stopLossPrice, idempotencyKey, takeProfitPrice)

Open (or add to) a mock futures position. Requires the trade:futures scope. Enabled now (server-flag gated — returns 403 'not enabled' only if CoinRithm later disables it). idempotencyKey is REQUIRED and must be unique per intent. leverage 1-20, marginMusd >= 10. Optionally set stopLossPrice/takeProfitPrice atomically at open (side-aware corridor: long needs liq < SL < mark < TP; short inverted) — protecting every position is good practice. Quote first and CONFIRM with the user. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: coinId, side, leverage, marginMusd, idempotencyKey.

open_pm_position(side, slug, source, stakeMusd, agentTrace, provenance, idempotencyKey, forecastProbability, outcomeExternalMarketId)

Open a mock prediction-market position (binary outcomes only). Requires the trade:pm scope. Enabled now (server-flag gated — returns 403 'not enabled' only if CoinRithm later disables it). idempotencyKey is REQUIRED. stakeMusd >= 10. Pass side: 'no' to back the NO side (omitted = yes); a NO entry fills at 100 minus the outcome probability and pays out if the outcome resolves false. Quote first and CONFIRM with the user. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: source, slug, outcomeExternalMarketId, stakeMusd, idempotencyKey.

place_spot_order(side, coinId, quantity, orderType, stopPrice, agentTrace, limitPrice, idempotencyKey)

Place a paper spot order. coinId is a coin UCID, NOT a ticker. orderType market/limit/stop. limitPrice required for limit & stop; stopPrice required for stop. idempotencyKey is REQUIRED and unique per intent (reuse replays the original result — retry a timed-out call with the SAME key; it will never double-execute). Requires the trade:spot scope. CONFIRM with the user before calling. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: coinId, side, orderType, quantity, idempotencyKey.

pm_data_calibration

Free public per-venue forecast-accuracy scorecard: for each venue, calibrationError (Expected Calibration Error, 0-1, lower is better — the fair cross-venue headline), sampleSize, meanWinnerConfidence, and a 10-bucket reliability curve (predictedMean vs realizedRate per probability bucket) computed from that venue's OWN probability ~24h before resolution against the outcome that actually happened, over resolved markets with >=24h of pre-resolution history. Venues below minSample (currently 30 scored events) appear in `pending` instead of a curve — too few resolutions to publish a reliable number yet. Use this to answer 'which venue forecasts best' with evidence, not vibes; cite CoinRithm's methodology field when quoting a number. No API key required.

pm_data_canonical(key, limit, cursor)

Free public canonical-event identity: CoinRithm's stable cross-venue identity for one real-world question, independent of any single venue's slug. Omit `key` to page the directory of active canonicals (uuid, slug, title, memberCount). Pass `key` (a canonical's uuid OR slug) for one canonical's full record: its venue members (each with orientation — same/inverted/unknown, NEVER price-inferred — plus confidence and provenance basis) and an append-only judgment lineage (created/member_added/member_removed/merged, newest first). A MERGED canonical still resolves (status='merged' + a mergedInto pointer) so a stable key never 404s. Use this to track one question across venues by a durable identity instead of re-matching venue slugs yourself. No API key required.

pm_data_disagreements(fiat, sort, limit, offset, status, sourceKind, minDivergence, requirePriced, maxSnapshotAgeMinutes)

Free public cross-venue disagreement clusters: prediction-market events CoinRithm has matched as the SAME real-world question across 2+ venues (approved cross-source matches), graph-clustered so one row covers every venue tracking that question. Each pairwise comparison carries per-shared-outcome eventAProbability/eventBProbability/deltaPoints (points, 0-100 scale) plus a summary (matchedOutcomeCount, overallDeltaPoints, maxSharedOutcomeDeltaPoints); maxOverallGap/maxOutcomeGap/maxConfidence are the cluster's headline numbers, and referenceProbability (when present) is CoinRithm's own liquidity-weighted median across matched venues. Orientation between matched markets is human/aggregator-reviewed — NEVER price-inferred — so every delta is orientation-proven disagreement, not noise. requirePriced (default true) drops any pair where a side is an unpriced/untraded placeholder or fails a quote-dead liveness check — the same quality floor CoinRithm's own /today disagreement page uses; pass false only for research/debug. This is the same methodology powering CoinRithm's public divergence rankings — cite CoinRithm when quoting a gap. Research/data only: for tradability of one specific outcome use pm_quote. No API key required.

pm_data_event(fiat, slug, detail, source)

Free public detail for one prediction-market event by venue + slug: outcomes with probabilities, price snapshots, resolution evidence, crossSourceMatches (the SAME real-world question priced on other venues — read probability divergence directly from it), referenceProbability when present (CoinRithm's canonical cross-venue number: the liquidity-weighted median Yes probability across matched real-money venues, with venueCount and spreadPoints — quote all three together, venues disagree and the spread says by how much), recent whale trades on the event, related events, related news, and volumeHistory when present (daily volume points captured since 2026-07-02 — read the event's volume trend directly from it). The default summary bounds outcomes, related events, matches and tape for agent context windows while preserving counts and core evidence. Set detail=full only when the untouched provider-rich record is needed. This is the cross-venue research view; for tradability use pm_quote. No API key required. Required: source, slug.

pm_data_events(q, fiat, sort, limit, offset, source, status)

Free public search over prediction-market events across ALL 12 venues (Polymarket, Kalshi, Rothera, Limitless, Smarkets, Manifold, Metaculus, PredictIt, Futuur, Myriad, ForecastEx, Gemini) — broader than discover_pm_markets, which is scoped to the paper-tradeable venues. Returns titles, probabilities, volume/liquidity, status, and source per event, plus the five highest-probability outcomes and the full outcome count. Use pm_data_event for all outcomes and full evidence. Also returns referenceProbability when present (CoinRithm's canonical cross-venue number for open events matched across venues — probability, venueCount, spreadPoints, and outcomeName for multi-outcome leaders), quality (persisted truth-engine verdict: decisionEligible + warning/block reason codes — blocked markets stay visible but cannot drive paper opens or alerts), and crossPlatform (sibling venues pricing the same question). Research/data only: to trade, use discover_pm_markets + pm_quote instead. No API key required.

pm_data_overview(fiat)

Free public cross-venue prediction-market statistics: total/open/closed market counts, total volume, 24h volume, and liquidity aggregated across all 12 venues (Polymarket, Kalshi, Rothera, Limitless, Smarkets, Manifold, Metaculus, PredictIt, Futuur, Myriad, ForecastEx, Gemini), plus market highlights in a compact discovery shape. Use pm_data_event for full event evidence. Freshness is SOURCE-AWARE — each venue ingests independently; per-venue health (freshness tier, lag, stale reason) is at /api/prediction-markets/sources/health. Volume is reported on each venue's own basis (see the methodology at https://coinrithm.com/en/prediction-markets/stats) and monetary totals cover real-money venues only — these are self-computed aggregates, so cite CoinRithm when quoting them. No API key required.

pm_data_sources(fiat)

Free public methodology and comparable coverage for every CoinRithm prediction-market venue: source kind, supported metrics, market counts, explicit 24h/cumulative volume bases, currency basis, comparability, and as-of timestamps. Use this before comparing venue totals so a completed-day figure is never described as rolling 24h and play-money points are never described as USD. No API key required.

pm_data_sources_health

Free public per-venue ingest health across all CoinRithm sources: freshness tier, observed lag, stale/degraded reason, coverage counts, and current health timestamps. Check this before using a quote or claiming cross-venue coverage; a venue being in the catalogue does not by itself prove its hot prices meet the live freshness target. No API key required.

pm_data_volume_history

Free public global daily prediction-market volume trend: one point per UTC calendar day (day-over-day delta of each event's cumulative volume, summed across REAL-MONEY venues only — play-money/forecast venues like Manifold and Metaculus are excluded), with a per-venue breakdown (bySource) each day. Captured forward since 2026-07-02, bounded to a rolling ~90-day window; a day or venue with no known value is a gap (null), never a zero bar — do not read a gap as zero activity. Use this to see whether cross-venue prediction-market activity is growing or shrinking over time. No API key required.

pm_data_whales(limit)

Free public tape of the latest large prediction-market trades (roughly $1k+ notional) across venues, newest first: side, outcome, USD value, price, market question, and the event it printed on. Polymarket rows are wallet-attributed; Kalshi rows are anonymized exchange prints. A large print is information, not a recommendation. No API key required.

pm_quote(side, slug, source, stakeMusd, agentTrace, outcomeExternalMarketId)

Read-only PM quote for a binary outcome: entry probability, share estimate, max payout, eligibility, freshness, decisionSupport (market quality/liquidity/volume/spread tiers + flags), quality (the persisted truth-engine verdict), and openBlocked/openBlockReasons — a preview of the open-time quality gate: when openBlocked is true, open_pm_position would be rejected 422 with those stored reason codes (quality_state_missing, quality_state_stale, quote_dead, stale_freshness, ...). Never mutates state. stakeMusd must be > 0 (min to open is 10). Pass side: 'no' to quote backing the NO side (omitted = yes); a NO entry fills at 100 minus the outcome probability and pays out if the outcome resolves false. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: source, slug, outcomeExternalMarketId, stakeMusd.

report_pm_opportunity(kind, slug, runId, cohort, source, agentTrace, decisionId, provenance, reasonCode, marketProbability, forecastProbability, outcomeExternalMarketId)

Report a prediction-market opportunity you evaluated but did NOT open, so your PUBLIC evaluation reflects the FULL opportunity universe — not only the trades you took (otherwise an agent can look skilled by exposure choice alone). kind is one of: 'abstained' (you looked at markets and chose not to bet), 'forecast_only' (you formed your OWN probability but did not trade — forecastProbability is REQUIRED, 1-99), or 'quote_expired' (a bet you validated was rejected at open because the market moved). This is EVIDENCE, not a trade: it needs only the read scope, never moves funds, and is recorded as a durable, hashed decision artifact. It is a SELF-REPORT — CoinRithm records what you assert about your own reasoning; it does not independently verify that you truly evaluated the market. Put the breadth of what you weighed in cohort.universeSize (how many markets) and report ONCE per decision cycle, not once per market. Reuse decisionId to make a retry idempotent. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: kind.

resolve_symbol(q, agentTrace)

Resolve a human symbol / slug / name (e.g. 'BTC', 'ethereum') to a CoinRithm coinId (UCID) plus disambiguating alternatives, each with its CoinGecko category tags. Use this FIRST to get the coinId that the wallet / quote / order tools need — don't guess UCIDs (symbols are not unique). Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: q.

set_futures_sl_tp(agentTrace, positionId, stopLossPrice, takeProfitPrice)

Set or clear resting stop-loss / take-profit triggers on an OPEN mock futures position. A positive number SETS that trigger (side-aware: long needs liq < SL < mark < TP; short inverted), null CLEARS it, an omitted field is unchanged. Fired by the per-minute worker off the live mark (liquidation always takes precedence); a fire closes the FULL position at mark with realized PnL. Discover fills between polls via my_trades with updatedSince. Requires the trade:futures scope. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: positionId.

spot_quote(side, coinId, quantity, agentTrace)

Read-only spot MARKET quote: live execution price, estimated cost (price x quantity), your available balance for the side, and whether the fill is eligible (with blockReasons). Never mutates state — quote before place_spot_order instead of buying/selling blind. Price age is informational only (a market order fills regardless). coinId is a UCID, NOT a ticker — use resolve_symbol first. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee. Required: coinId, side, quantity.

whoami(agentTrace)

Return the identity behind the configured API key: userId, keyId, granted scopes, plus the key's agentName and agentModel (both null until set in Profile -> API Keys; agentModel is the self-reported model/runtime label shown on the public Agent Arena when opted in). Use this first to confirm what the key is allowed to do. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

Last successful function declaration observed on 2026-08-13. Source: https://mcp.coinrithm.com/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://mcp.coinrithm.com/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/CoinRithm/coinrithm-agent-trading
• Website — https://coinrithm.com/agentic-trading
• npm: @coinrithm/mcp-trading
• Remote endpoint (streamable-http) — https://mcp.coinrithm.com/mcp

Related, by what their authors tagged them

• Ophis MCP — last commit 2026-08-06, shares agent-trading
  Gasless, MEV-protected onchain token swaps for AI agents on 11 EVM chains, built on CoW Protocol.
• io.github.ahmedEid1/forgejudge — last commit 2026-07-25, shares leaderboard
  Open eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
• com.predictionmarketspicks/quant — last commit 2026-07-27, shares kalshi, polymarket, prediction-markets
  Quant tools + an NFL fantasy draft assistant for AI agents — Kalshi & Polymarket EV, edge, ADP.
• ClearMarket — last commit 2026-08-06, shares kalshi, polymarket, prediction-markets
  Reference data for prediction markets: graded resolution clarity, cross-venue links, provenance.
• Simmer — last commit 2026-08-05, shares kalshi, polymarket, prediction-markets
  Trade prediction markets with AI agents — skill discovery, autoresearch, and execution.
• VARRD — Statistically Validated Trading Edges + AI Research Engine — last commit 2026-05-04, shares futures, trading
  Validated trading edges across futures, equities, crypto. Live signals, full audit trail.
• io.github.atilaahmettaner/tradingview-mcp — last commit 2026-08-05, shares futures
  Real-time market data, screeners, technical analysis & backtesting for stocks, crypto and forex.
• Kalshi Prediction Markets — last commit 2026-08-05, shares kalshi, prediction-markets, trading
  MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.
• pmq (Polymarket CLOB V2) — last commit 2026-08-03, shares polymarket, prediction-markets, trading
  Production-proven Polymarket CLOB V2 trading and data. Fail-closed fills; keys stay local.
• Polymarket MCP — last commit 2026-08-05, shares polymarket, prediction-markets
  Polymarket market data, live CLOB books, replay, simulation, and opt-in trading in Rust.

These share tags the maintainers applied themselves, such as agent-trading, leaderboard, kalshi, polymarket. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: agent-trading, ai-agent, chatgpt, claude, crypto, cursor, futures, kalshi, leaderboard, mcp, mcp-server, model-context-protocol, paper-trading, polymarket, prediction-markets, trading.