Polyrank MCP
OfficialSummary: Polyrank MCP gives AI agents read-only access to a skill-ranked analytics layer for Polymarket — finding skilled traders, checking their calibration, and seeing smart-money consensus — with optional keyed tools for custom rankings and AI Lab backtesting.
Find skilled traders —
polyrank_get_leaderboardreturns top wallets by composite skill score (calibration/Brier, alpha-vs-mid, risk-adjusted return), with rank, P&L, win rate and volume.Profile a wallet —
polyrank_get_trader_skillgives composite rank, P&L, win rate, volume, trades/markets and percentiles (deeper skill grid is gated to the paid x402 tier).Check calibration —
polyrank_get_trader_calibrationreturns a 10-bin reliability diagram, the core skill signal of predicted vs. observed outcomes.Read market consensus —
polyrank_get_market_consensusshows skill-weighted holder consensus vs. market mid, plus 24h volume, positioners and top holders for a conditionId or slug.See what smart money is doing now —
polyrank_get_pulsesurfaces big wins, sharp moves, biggest trades, trending markets and divergence.Track momentum —
polyrank_get_moverslists traders climbing or falling fastest in skill rank over a lookback window.Browse top single trades —
polyrank_get_top_roi_tradesranks resolved bets by ROI, filterable by category and recency (identities masked).Read weekly research —
polyrank_get_smart_money_reportslists the Smart-Money Report archive;polyrank_get_smart_money_reportfetches one week in full.Follow masked traders —
polyrank_get_trader_by_tidresolves an opaquetidfrom masked rows into a skill teaser (raw wallet requires sign-in).Check data coverage —
polyrank_get_platform_statsreports wallets ranked, trades indexed, markets covered and metric count.With a Polyrank API key (per README) — custom rankings via the Builder (
polyrank_rank_wallets, any of 84 metrics/windows/filters,as_of), full per-window trader metrics,polyrank_resolve_tid, metrics catalog/templates, and AI Lab tools (strategy creation, backtests, paper trading, AI assistant chats — simulated results).*Hosted or local — usable via OAuth sign-in on
https://mcp.polyrank.app/mcp, the keyless public endpoint (17 free tools), or run locally over stdio.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Polyrank MCP show me the top traders by skill"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@polyrank/mcp
MCP server that gives AI agents (Claude, etc.) direct access to Polyrank —
the skill-analytics layer for Polymarket. It ranks millions of Polymarket
wallets by genuine forecasting skill (calibration / Brier, alpha-vs-mid,
risk-adjusted return) — not vanity P&L or win rate. Follow the skilled, not the
lucky. (Live coverage + the exact skill-metric count: polyrank_get_platform_stats.)
The public tools wrap Polyrank's free API — no key. With a Polyrank API key
(POLYRANK_API_KEY, from polyrank.app/api-keys on a plan with the Ranking
Builder / AI Lab), the ranking, trader-metrics and AI Lab tools call the
authenticated API: the same POST /v1/rankings/custom the Ranking Builder runs —
any of the 84 metrics at any window it exists at, every filter, as_of boards —
plus per-window trader metrics and backtests / paper trading. Agents that pay per
call instead of holding a key use the x402 agent API — see https://polyrank.app/llms.txt.
Every tool carries a title and the MCP annotations readOnlyHint, destructiveHint, idempotentHint and
openWorldHint: 29 tools are read-only; the 7 AI Lab writes (polyrank_create_strategy,
polyrank_run_backtest, polyrank_start_paper, polyrank_update_strategy, polyrank_lab_ask, polyrank_lab_reply,
polyrank_lab_stop) each create or change a record in your own Polyrank account and are marked
destructiveHint: false (none deletes anything, none touches funds; the chat tools spend your plan's AI credits).
Read-only tools are listed first.
Free tools (read-only, no key) — 17
Tool | What it does |
| Top traders ranked by composite skill |
| A wallet's P&L / win-rate / volume / percentiles |
| A wallet's 10-bin reliability diagram |
| Skill-weighted holder consensus vs market mid + top holders |
| Live activity: big wins, sharp moves, trending, divergence |
| Live coverage + skill-metric count (wallets/trades/markets) |
| Biggest return-on-cost resolved trades (filter by category) |
| Traders climbing / falling fastest in skill rank |
| Weekly Skill Report archive |
| One weekly Skill Report in full |
| Follow a masked trader by its |
| A masked trader's 10-bin reliability diagram by |
| A published Builder ranking: masked top-25 + weight/filter def |
| Masked teasers for up to 10 |
| The 84 rankable metrics: id, meaning, direction, windows |
| Which metric exists at which window; what |
| The Builder's goals ("Copy entries", …) as ready requests + presets |
Related MCP server: Polymarket MCP Server
Ranking + trader tools (need POLYRANK_API_KEY) — 3
Tool | What it does |
| Resolve a masked |
| The Ranking Builder: weights × windows × filters, |
| One trader's every metric at a window: value + percentile (address or |
AI Lab tools (need POLYRANK_API_KEY on a paid plan with the AI Lab; results are SIMULATED) — 16
Tool | What it does |
| Strategy templates (editable specs) with their as-of evidence |
| Save a strategy (spec or template) |
| Queue a backtest of a strategy or spec over a date range |
| A backtest's status and report |
| Start paper trading a strategy against real order books (no money) |
| A paper run's stats and its copies |
| Your strategies, filtered by state (draft, tested, paper…) |
| One strategy with its full spec |
| Your recent backtests, all or one strategy's |
| Your plan's AI Lab limits and what is used, incl. chats at once |
| Your AI Lab assistant chats |
| One chat: answers, result cards, queue position |
| Rename a strategy or replace its spec |
| Ask the AI Lab assistant in a new chat (spends AI credits) |
| Reply in a chat (spends AI credits) |
| Stop an answer |
The AI Lab tools act as your own Polyrank account: a plan with the AI Lab (Pro Trader and up; a strategy that copies
no wallet needs Lab Pro and up), each backtest counting against the plan's backtests a day, with queue_position and
eta_s on a queued run. Plans and limits: https://docs.polyrank.app/lab.
The AI Lab assistant (polyrank_lab_ask, polyrank_lab_reply): the same assistant as polyrank.app/lab, acting in
your account (research only; it never places orders). Each question spends your plan's AI credits (25 needed to start,
a typical one about 13; deep: true about twice) and your plan answers a number of chats at once (Pro Trader 2, Lab
Pro 3, Quant 4, Quant Max 6, Desk 6, Enterprise 8; one more answers 429 lab_agent_busy). The tool waits up to
wait_seconds (default 45, at most 55) for the answer, then returns what is there; poll polyrank_lab_get_chat while
next says it is still answering. A backtest the assistant starts that takes longer than a few seconds runs on:
awaiting_backtests counts them, and each result is posted to the chat when it finishes. Every answer, and every AI Lab
result with simulated figures (polyrank_run_backtest, polyrank_get_backtest, polyrank_get_paper_run,
polyrank_list_strategies, polyrank_list_backtests), comes with the CFTC Rule 4.41 statement
(simulated_results_notice).
Reproduce a Builder board (e.g. "Copy entries", top 20): call
polyrank_list_ranking_templates, then polyrank_rank_wallets with that goal's request.
Install
Claude Code
claude mcp add polyrank -- npx -y @polyrank/mcpClaude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"polyrank": { "command": "npx", "args": ["-y", "@polyrank/mcp"] }
}
}Cursor — add to .cursor/mcp.json (same block as above), or use the one-click deep link:
VS Code
code --add-mcp '{"name":"polyrank","command":"npx","args":["-y","@polyrank/mcp"]}'Config: POLYRANK_API_BASE (default https://api.polyrank.app),
POLYRANK_AGENT_BASE (default https://api-agent.polyrank.app; only its free
manifests are read), and optional POLYRANK_API_KEY, which unlocks the ranking,
trader-metrics, AI Lab and tid-resolve tools. With a key:
claude mcp add polyrank -e POLYRANK_API_KEY=pk_live_… -- npx -y @polyrank/mcpHosted (Streamable HTTP)
Polyrank hosts this server at https://mcp.polyrank.app (Streamable HTTP), so nothing needs installing:
Endpoint | Tools |
| all 36: the 17 free tools without sign-in; the other 19 after sign-in (OAuth 2.1: your MCP client opens Polyrank's sign-in and consent) or with |
| the 17 free read-only tools only; any Authorization header is ignored |
| status and version |
In Claude (Settings → Connectors → Add custom connector), ChatGPT or Cursor, add https://mcp.polyrank.app/mcp. In
Claude's dialog choose Sign in now to connect your account up front (otherwise the free tools work and the app asks
you to sign in at the first tool that needs your account): you sign in to Polyrank and approve what the app may do
(read data; your AI Lab, optional). Disconnect it any time in Polyrank → Account → Connected apps. With a key
instead:
claude mcp add --transport http polyrank https://mcp.polyrank.app/mcp --header "Authorization: Bearer pk_live_…"claude mcp add --transport http polyrank-free https://mcp.polyrank.app/mcp/publicIt is for MCP clients and agent backends, not for pages in a browser: a request that carries a browser Origin header
is refused (403). Limits: 100 requests a minute per address without sign-in or a key, 600 a minute with one, and your
plan's API limits behind them. The 16 AI Lab tools need a paid plan with the AI Lab; their results are simulated.
The package also runs this server itself (MCP_HTTP_ENABLED=1); with no flag it is the stdio server above.
Run it yourself: MCP_HTTP_ENABLED=1 MCP_HTTP_PORT=3005 npx -y @polyrank/mcp, then
curl -s localhost:3005/healthz. Options (env): MCP_HTTP_HOST (default 127.0.0.1), MCP_HTTP_PORT (3005),
MCP_HTTP_ALLOWED_HOSTS (Host header allow-list, default mcp.polyrank.app,localhost,127.0.0.1,[::1]),
MCP_HTTP_ALLOWED_ORIGINS (browser Origin allow-list, default none), MCP_HTTP_ANON_PER_MIN (100),
MCP_HTTP_KEY_PER_MIN (600), MCP_HTTP_VERIFY_KEYS (1), MCP_HTTP_MAX_BODY_BYTES (1048576),
MCP_FORWARD_CLIENT_IP (0). In HTTP mode POLYRANK_API_KEY is ignored: every caller sends their own key.
Details: src/http.ts.
Not affiliated with Polymarket · not investment advice · not custodial.
Available Tools
11 toolspolyrank_get_leaderboardPolyrank skill leaderboardARead-onlyInspect
Top Polymarket traders ranked by genuine SKILL (calibration/Brier, alpha-vs-mid, risk-adjusted return) — not vanity P&L or win rate. Returns rank, composite score, identity, P&L, win-rate, volume. Use this to find traders worth copying or studying.
Inputs: limit, preset.
polyrank_get_market_consensusPolyrank market consensusARead-onlyInspect
Smart-money consensus on a Polymarket market vs the market mid (the Polyrank-vs-mid delta is a differentiated signal), plus 24h volume/fills, positioner counts, and top holders. Accepts a conditionId (0x + 64 hex) or a market slug.
Inputs: market (required).
polyrank_get_moversPolyrank skill-rank moversARead-onlyInspect
Traders whose skill rank climbed or fell the most recently (leaderboard momentum). Returns top climbers and fallers for a ranking preset over a lookback window.
Inputs: limit, preset, lookback_days.
polyrank_get_platform_statsPolyrank platform coverage & metric countARead-onlyInspect
Live Polyrank coverage and the canonical skill-metric count: total wallets ranked, trades indexed, markets covered, the number of skill metrics in the catalog, and the earliest year of data. Use this instead of hardcoding "N wallets / N metrics".
Inputs: no named parameters.
polyrank_get_pulsePolyrank live pulseARead-onlyInspect
Live Polymarket activity: big wins just banked (realized profit), sharp-money moves, the biggest recent trades, trending markets by volume, and markets where Polyrank consensus diverges most from the market mid. Good for "what is smart money doing right now".
Inputs: no named parameters.
polyrank_get_smart_money_reportPolyrank Smart-Money Report (one week)ARead-onlyInspect
One Polyrank weekly Smart-Money Report in full: big wins, skill-rank movers, new entrants, the calibration leader, consensus divergence, and the editorial intro. Pass the week/report id from polyrank_get_smart_money_reports.
Inputs: week (required).
polyrank_get_smart_money_reportsPolyrank Smart-Money Report archiveARead-onlyInspect
The archive of Polyrank weekly Smart-Money Reports (published each week): a list of report ids/weeks with summaries. Fetch one in full with polyrank_get_smart_money_report.
Inputs: limit.
polyrank_get_top_roi_tradesPolyrank highest-ROI resolved tradesARead-onlyInspect
The biggest return-on-cost RESOLVED Polymarket bets (won positions with a real cost floor) — a hall-of-fame of single trades by ROI multiple. Optionally filter by market category (e.g. "Sports", "Politics", "Crypto"). Identities are masked (pseudonym only).
Inputs: dir, sort, limit, category, +1 more.
polyrank_get_trader_by_tidPolyrank trader teaser (by masked id)ARead-onlyInspect
Look up a trader by the opaque masked id (tid) returned in leaderboard / pulse / movers / top-ROI rows — those masked surfaces omit the raw wallet, so use the tid to follow a trader. Returns the same masked skill teaser as the wallet lookup. Full wallet/identity resolution requires signing in on polyrank.app.
Inputs: tid (required).
polyrank_get_trader_calibrationPolyrank trader calibrationARead-onlyInspect
A wallet’s 10-bin reliability diagram (predicted probability vs observed outcome rate). Calibration is the core skill signal — whether the trader’s probabilities match reality. Returns bins + total resolved count.
Inputs: address (required).
polyrank_get_trader_skillPolyrank trader skill profileARead-onlyInspect
A single Polymarket wallet’s skill profile: composite rank, P&L, win-rate, volume, trades/markets, and commodity percentiles. The deep skill grid — full Brier decomposition, alpha-vs-mid, information coefficient, Sharpe, copyability & max copyable clip, true slippage, realized volatility, the hold-time split, peak/avg capital-at-risk, copier-realized return, and the copy verdict — is gated to the paid x402 agent tier (/v1/agent/*).
Inputs: address (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
All tools have clearly distinct purposes: leaderboard, market consensus, movers, platform stats, pulse, smart money reports (list and get), top ROI trades, trader lookup by tid, trader calibration, and trader skill. No overlapping functionality.
All tool names follow a consistent 'polyrank_get_<noun>' pattern with snake_case, making them predictable and easy to understand.
11 tools is well-scoped for the analytics domain. Each tool covers a distinct aspect of the Polyrank platform without being excessive or insufficient.
The tool set covers leaderboard, market consensus, trader profiles, and smart money reports. Minor gaps exist, such as no tool for listing all markets or retrieving a trader's full trade history, but the core functionality is present.
Maintenance
Related MCP Connectors
Polymarket in your AI: market rules, real fill costs, who is trading, top traders. Read-only.
Live Polymarket data for agents: markets, insider-scored whale trades, leaderboards, wallet P&L
Polymarket wallet intelligence for AI agents: scored wallets, insider signals, whale flow.
Unofficial, read-only Polymarket analytics: top markets, movers, related-market mispricing checks.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to query Polymarket prediction markets, accessing real-time odds, market data, price history, order books, and trending markets across categories like politics, crypto, and sports through natural language.46 npm7MIT
- AlicenseBqualityDmaintenanceEnables comprehensive read access to Polymarket prediction market data, including live prices, order books, and market statistics. It allows AI assistants to analyze events, search markets, and monitor real-time signals without requiring API keys or authentication.221MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to interact with Polymarket prediction markets, including retrieving market data, user positions, and trading history.823 npm13Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to query Polymarket data such as top wallets, live trades, market details, and smart money flows using natural language through MCP tools.MIT