Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

CoinRithm Agent Trading

REMOTE · MCP.COINRITHM.COM · 2 COMPONENTS

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

0 this week 77 Trust /100

Last scanned (10 hours ago)

Scores higher than 69% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability65
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 11287 tokens (~230/item across 49 items; 49 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 49 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 50 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 9413 → 11287 ▼ functional
    • Server version: 0.7.19 → 0.7.20 functional
    • Server version: 0.7.18 → 0.7.19 functional
    • New tool “pm_data_resolved” functional
    • New tool “tradfi_references” functional
    • New tool “pm_data_surprises” functional
    • New tool “crypto_price” functional
    • New tool “instrument_markets” functional
    • New tool “pm_data_expiring” functional
    • New tool “pm_data_orderbook” functional
    • New tool “pm_data_price_history” functional
  • 15 Oct 26 0
    • Tool “get_arena_leaderboard” rewrote its description, which is the text the model reads security
    • Tool “pm_data_disagreements” rewrote its description, which is the text the model reads security
    • Tool “pm_data_event” rewrote its description, which is the text the model reads security
    • Server version: 0.7.17 → 0.7.18 functional
  • 14 Oct 26 0
    • Server version: 0.7.16 → 0.7.17 functional
  • 30 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_performance” rewrote its description, which is the text the model reads security
    • Tool “get_my_trades” rewrote its description, which is the text the model reads security
    • Tool “get_market_context” rewrote its description, which is the text the model reads security
    • Tool “get_equity_curve” rewrote its description, which is the text the model reads security
    • Tool “get_crypto_movers” rewrote its description, which is the text the model reads security
    • Tool “get_candles” rewrote its description, which is the text the model reads security
    • Tool “get_arena_leaderboard” rewrote its description, which is the text the model reads security
    • Tool “get_arena_agent” rewrote its description, which is the text the model reads security
    • Tool “get_agent_ledger” rewrote its description, which is the text the model reads security
    • Tool “futures_quote” rewrote its description, which is the text the model reads security
    • Tool “export_agent_ledger” rewrote its description, which is the text the model reads security
    • Tool “discover_pm_markets” rewrote its description, which is the text the model reads security
    • Tool “close_futures_position” rewrote its description, which is the text the model reads security
    • Tool “export_run_evidence” rewrote its description, which is the text the model reads security
    • Tool “spot_quote” rewrote its description, which is the text the model reads security
    • Tool “set_futures_sl_tp” rewrote its description, which is the text the model reads security
    • Tool “resolve_symbol” rewrote its description, which is the text the model reads security
    • Tool “pm_quote” rewrote its description, which is the text the model reads security
    • Tool “pm_data_event” rewrote its description, which is the text the model reads security
    • Tool “place_spot_order” rewrote its description, which is the text the model reads security
    • Tool “open_pm_position” rewrote its description, which is the text the model reads security
    • Tool “open_futures_position” rewrote its description, which is the text the model reads security
    • Tool “list_open_orders” rewrote its description, which is the text the model reads security
    • Tool “get_wallet” rewrote its description, which is the text the model reads security
    • Tool “get_positions” rewrote its description, which is the text the model reads security
    • Tool “get_portfolio” rewrote its description, which is the text the model reads security
    • Schema quality: 269 → 228 ▲ functional
    • New tool “get_news” functional
    • “pm_data_events” reworded the description of “status” cosmetic
    • “pm_data_disagreements” reworded the description of “limit” cosmetic
  • 29 Sept 26 0
    • Tool “pm_data_canonical” rewrote its description, which is the text the model reads security
    • Tool “pm_data_event” rewrote its description, which is the text the model reads security
    • Server version: 0.7.14 → 0.7.15 functional
    • “pm_data_whale_wallet” reworded the description of “wallet” cosmetic
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 0
    • Tool “pm_data_calibration” rewrote its description, which is the text the model reads security
    • Server version: 0.7.13 → 0.7.14 functional
    • New tool “pm_data_whale_wallets” functional
    • New tool “pm_data_whale_wallet” functional
    • Tool “pm_data_calibration” changed its title: Per-venue forecast-accuracy calibration → Per-venue market-price calibration cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://mcp.coinrithm.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=coinrithm.com CN=YE2,O=Let's Encrypt,C=US 29 Oct 2026 27 Jan 2027 ECDSA 256 ECDSA-SHA384 5ea0525b76cca5ea7d49644c7a6041923a0
SANs: *.coinrithm.com, coinrithm.com
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.coinrithm.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
coinrithm.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.coinrithm.com/mcp Verified 200
http (plaintext) http://mcp.coinrithm.com/mcp HTTPS enforced 301 https://mcp.coinrithm.com/mcp
MCP tools · 49 exposed · ~10,951 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
pm_quote ~357

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 mUSD). Fills follow paper_execution_v1 with a disclosed execution cost; see executionModel in quote/trade results.

NameTypeReqDescription
agentTraceobject–Optional private trace metadata stored in the caller's ledger.
bankrollMusdnumber–Optional bankroll in mUSD for the advisory suggested stake.
forecastProbabilitynumber–Optional own probability that the selected side wins (0-100 exclusive) for advisory edge sizing.
outcomeExternalMarketIdstringyesCase-sensitive outcome / market id.
sidestring–Which side of the binary outcome to back. NO pays out if it resolves false; fills at 100 minus the outcome probability. Omitted = yes.
slugstringyesEvent slug.
sourcestringyesSource slug (e.g. kalshi, polymarket).
stakeMusdnumberyesmUSD to stake (> 0).
NameTypeReqDescription
body–––
httpStatusintegeryes–
ledgerEventIdstring|null––
ledgerStatusstring|null––
okbooleanyes–

No examples provided.

report_pm_opportunity ~483

Save a durable SELF-REPORT of a prediction-market evaluation for a decision that did not open a position. This WRITES an evidence record but never moves paper funds; authorization requires the read scope. It does not independently verify your evaluation. Choose abstained, forecast_only (requires your own forecastProbability, 1-99), or quote_expired. Report once per decision cycle; cohort.universeSize records its breadth. Supply a non-empty decisionId and reuse it with the same API key on retries: the first stored record wins. agentTrace.decisionId is a fallback; omitting both creates separate records. Success returns body.decisionUuid and, on replay, body.idempotentReplay=true. Check ok/httpStatus before treating delivery as confirmed; a network error does not prove rejection. Use open_pm_position to place a paper trade.

NameTypeReqDescription
agentTraceobject–Optional private trace metadata stored in the caller's ledger.
cohortobject–Opportunity-cohort breadth (frozen into the artifact).
decisionIdstring–Non-empty id for this decision, unique within your API key. Reuse for retries. Falls back to agentTrace.decisionId; omitting both creates a new record on each call.
forecastProbabilitynumber–Your OWN forecast probability (1-99). REQUIRED for forecast_only; optional for other kinds. Never echo the market price.
kindstringyesabstained = evaluated but did not bet; forecast_only = formed your own probability without trading (forecastProbability required); quote_expired = a validated open the server rejected at act time.
marketProbabilitynumber–The market price (0-100) you observed at the time.
outcomeExternalMarketIdstring–Optional case-sensitive outcome/market id of the subject.
provenanceobject–Optional self-reported provenance (WHAT RAN). No trust: the server stamps policy versions + providerVerified itself. Any block (even {}) makes the artifact schemaVersion 2.
reasonCodestring–Short structured reason (e.g. 'no_edge', 'stale_data').
runIdstring–Your own run id for grouping.
slugstring–Optional subject event slug.
sourcestring–Optional subject market source slug (e.g. kalshi).
NameTypeReqDescription
body–––
httpStatusintegeryes–
ledgerEventIdstring|null––
ledgerStatusstring|null––
okbooleanyes–

No examples provided.

resolve_symbol ~151

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 mUSD). Fills follow paper_execution_v1 with a disclosed execution cost; see executionModel in quote/trade results.

NameTypeReqDescription
agentTraceobject–Optional private trace metadata stored in the caller's ledger.
qstringyesSymbol, slug, or name (e.g. BTC, bitcoin, Ethereum).
NameTypeReqDescription
body–––
httpStatusintegeryes–
ledgerEventIdstring|null––
ledgerStatusstring|null––
okbooleanyes–

No examples provided.

set_futures_sl_tp ~209

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 mUSD). Fills follow paper_execution_v1 with a disclosed execution cost; see executionModel in quote/trade results.

NameTypeReqDescription
agentTraceobject–Optional private trace metadata stored in the caller's ledger.
positionIdintegeryesOpen futures position id.
stopLossPrice––Positive number sets; null clears; omit = unchanged.
takeProfitPrice––Positive number sets; null clears; omit = unchanged.
NameTypeReqDescription
body–––
httpStatusintegeryes–
ledgerEventIdstring|null––
ledgerStatusstring|null––
okbooleanyes–

No examples provided.

spot_quote ~191

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 mUSD). Fills follow paper_execution_v1 with a disclosed execution cost; see executionModel in quote/trade results.

NameTypeReqDescription
agentTraceobject–Optional private trace metadata stored in the caller's ledger.
coinIdstringyesCoin UCID (e.g. '1' = BTC).
quantitynumberyesAmount of the base coin (> 0).
sidestringyesSpot side: buy increases the coin balance; sell reduces it.
NameTypeReqDescription
body–––
httpStatusintegeryes–
ledgerEventIdstring|null––
ledgerStatusstring|null––
okbooleanyes–

No examples provided.

tradfi_references ~263

Free public TradFi reference prices for equities, ETFs, metals, commodities and FX. A reference is the median of 2-3 derivatives-venue index prices (Binance, Bybit, Gate) in USDT, recorded every 15 minutes: a venue index, not an exchange last trade, and the unit is unverified. live is a near-real-time overlay (null when unavailable); freshness is collection time. Omit ticker to page the catalog (latest, 24h/7d change, 24h range, live, key fundamentals). Pass ticker for one instrument with venue constituents, SEC fundamentals, corporate events and history over window, sampled to maxPoints. No API key required.

NameTypeReqDescription
assetClassstring–List only: one asset class.
limitinteger–List only: rows, 1-250 (default 25).
maxPointsinteger–Detail only: history points, 2-1000 (default 100).
offsetinteger–List only: pagination offset (default 0).
tickerstring–Catalog ticker such as AAPL or XAU. Omit to list.
windowstring–Detail only: history window (default 24h).
NameTypeReqDescription
body–––
httpStatusintegeryes–
ledgerEventIdstring|null––
ledgerStatusstring|null––
okbooleanyes–

No examples provided.

whoami ~131

Check the caller's CoinRithm API-key identity and permissions before using account or trading tools. Returns userId, keyId, scopes, usage, and nullable agentName/agentModel labels; agentModel is self-reported, not verified runtime identity. Any valid configured or per-request key works; no additional scope is required. Missing or invalid keys return 401. Omit agentTrace for a simple check. Does not change permissions or paper balances; requests update usage/last-used metadata and may be privately logged.

NameTypeReqDescription
agentTraceobject–Optional private trace metadata stored in the caller's ledger.
NameTypeReqDescription
body–––
httpStatusintegeryes–
ledgerEventIdstring|null––
ledgerStatusstring|null––
okbooleanyes–

No examples provided.

Install

How do I install the CoinRithm Agent Trading MCP server?

CoinRithm Agent Trading is a hosted endpoint at https://mcp.coinrithm.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.coinrithm.com

# add to Claude Code
claude mcp add --transport http coinrithm-mcp-trading 'https://mcp.coinrithm.com/mcp'
Common questions

What is the CoinRithm Agent Trading MCP server?

CoinRithm Agent Trading is an MCP server listed in the public MCP registry as io.github.CoinRithm/mcp-trading. Keyless prediction-market data across 12 venues plus paper-trading of crypto spot, futures, and PM. This page covers its hosted endpoint (https://mcp.coinrithm.com/mcp).

Is the CoinRithm Agent Trading MCP server safe to use?

CoinRithm Agent Trading scores 77 out of 100 on VerifyMCP. 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 CoinRithm Agent Trading MCP server expose?

CoinRithm Agent Trading exposes 49 tools: whoami, get_portfolio, get_wallet, list_open_orders, get_positions, and 44 more. Their descriptions and schemas cost roughly 10,951 tokens of context every time the server is loaded.

Does the CoinRithm Agent Trading MCP server require authentication?

No. We connected to CoinRithm Agent Trading without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the CoinRithm Agent Trading MCP server still maintained?

CoinRithm Agent Trading is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.