Polyrank MCP Server

Writes to the user's Lab: ask the user before calling, then pass confirm: true. Save a strategy to your Lab: a name plus a strategy spec (wallet source — any Builder ranking, a history ranking, a static wallet list or a copy-engine sleeve — and market, entry, sizing and exit rules), or a template_id to copy a template. The server validates the spec and answers with the reason when it refuses. Needs POLYRANK_API_KEY.

A backtest by id: its status (queued / running / done / failed) and, when done, the full SIMULATED report (per-$10 P&L, copies, the no-selection control, without-best-wallet, capacity, funnel, per wallet, daily). Needs POLYRANK_API_KEY.

A published Polyrank Builder ranking: masked top-25 + the weight/filter definition. Builder rankings are custom skill leaderboards (a weighting over the metric catalog plus filters) that users publish and share by slug. Returns the masked top-25 rows and the ranking’s weight/filter definition. Pass the slug from a shared /r/<slug> link.

Your plan's Strategy Lab limits and what is used now: backtests a day and today's, backtests waiting, paper runs at once, saved strategies, the assistant chats answering at once (lab_agent_concurrent) against those answering now, and the AI credits: credits_balance (allowance left + top-ups), credits_used_today, daily_ceiling_credits (null: none), when the allowance resets, what a typical question costs. In credits, never dollars. Needs POLYRANK_API_KEY.

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 it to find traders to study.

Skill-weighted holder consensus on a Polymarket market vs the market mid (the Polyrank-vs-mid delta), plus 24h volume/fills, positioner counts, and top holders. Accepts a conditionId (0x + 64 hex) or a market slug.

Which metric exists at which window (lifetime / 90d / 30d / 7d / 24h), whether it can be weighted, gated or filtered, the copy-engine and entry-timing ids (lifetime-pinned), and what a back-dated board (as_of) can answer: its metrics, the filters it honours and the reason for each it refuses. The reference for ranking at a window or as_of. Free, no key.

The full catalog of displayable Polyrank metrics (84): id, name, description, category, direction (higher/lower is better), the windows each is available at, and whether it is advanced. This is the vocabulary for the weights, skill_gates and metric_filters of polyrank_rank_wallets. Free, no key.

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.

A paper run by id with the grader's stats (copies, resolved, P&L per $10, entry vs the leader, the paper gate) and its copies, each with its fate (copied / no_fill / leader_sold / capped / skipped + reason). Needs POLYRANK_API_KEY.

Live Polyrank coverage and the canonical skill-metric count: wallets scored (`wallets`), raw fill events indexed (`trades`), markets covered, the number of skill metrics in the catalog, and the earliest market year in the data (`since_year`; on-chain order-book fills start 2022-11-21): the live source for "N wallets / N metrics" figures.

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 are the big and sharp wallets doing right now".

One Polyrank weekly Skill 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.

The archive of Polyrank weekly Skill Reports (published each week): a list of report ids/weeks with summaries. Fetch one in full with polyrank_get_smart_money_report.

One of your strategies by id: its name, state and full strategy spec (wallet source, market, entry, sizing, exit). Edit it with polyrank_update_strategy. Needs POLYRANK_API_KEY.

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).

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.

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.

A trader’s 10-bin reliability diagram (predicted probability vs observed outcome rate) keyed by the opaque masked id (tid) from a leaderboard / pulse / movers / top-ROI row. Calibration is the core skill signal — whether the trader’s probabilities match reality. Completes the discovery → tid → calibration loop without needing the raw wallet. Returns bins + total resolved count.

One trader's every metric displayable at a window (lifetime / 90d / 30d / 7d / 24h): the raw value and its percentile in that window's cohort — the cells a board ranked at that window scores. Give a wallet address or a masked tid. scope=combined (default) reads the multi-wallet user row as boards do. Needs POLYRANK_API_KEY.

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/*).

Fetch the free masked skill teaser for several traders at once by their opaque masked ids (tids). Same per-trader payload as polyrank_get_trader_by_tid, capped at 10 tids per call. No API key needed. Each result is tagged with its tid, and per-tid failures are returned inline (as an error field) rather than failing the whole batch.

Spends the account's AI credits: ask the user before calling, then pass confirm: true. Start a Lab assistant chat with a question (research only: it finds traders, saves, backtests and paper-trades strategies in YOUR account, never places orders). Spends your plan's AI credits (a question needs 25 to start; a typical one costs about 13; `deep: true` runs the slower, more thorough mode, about twice the credits, Lab Pro and up). Your plan answers a number of chats at once (Pro Trader 2 … Enterprise 8; one more is refused 429 lab_agent_busy). Waits up to `wait_seconds` (default 45, max 55) for the answer; if it is still working, poll polyrank_lab_get_chat with the returned id. A long backtest it starts answers at once and its result is posted to the chat later. Results are SIMULATED. Needs POLYRANK_API_KEY.

One of your Lab assistant chats: its status, the questions and the assistant's answers with their notices and result cards (backtests, shortlists, strategies, tables). While a question waits, `queue_position` says how many are ahead; `awaiting_backtests` counts backtests the assistant started whose result will be posted to the chat by itself. Backtest and paper figures are SIMULATED. Needs POLYRANK_API_KEY.

Your Lab assistant chats, most recent first (at most 100): id, title, status (idle / queued / working / failed). Read one with polyrank_lab_get_chat. Needs POLYRANK_API_KEY (a paid plan; the assistant is part of every paid plan).

Spends the account's AI credits: ask the user before calling, then pass confirm: true. Send the next message in one of your Lab assistant chats (409 while it is still answering). Spends AI credits like polyrank_lab_ask and waits the same way for the answer. Needs POLYRANK_API_KEY.

Stop the Lab assistant answering in one of your chats: a question still queued is withdrawn; a running answer stops within about a second and keeps what it finished. A backtest it started keeps running. Needs POLYRANK_API_KEY.

Your recent backtests (all, or one strategy's), newest first, with status and headline (SIMULATED). Read one in full with polyrank_get_backtest. Needs POLYRANK_API_KEY.

The Strategy Lab's templates: research strategy families as editable strategy specs, each with its as-of evidence (SIMULATED, per $10 copied) and caveats. Copy one's `spec` (or its id) into polyrank_create_strategy / polyrank_run_backtest. Needs POLYRANK_API_KEY.

The Ranking Builder's goals (e.g. "Copy entries", "Copy engine") as the exact request the Builder runs for each, and the site's preset boards with their configs. Pass a goal's `request` (or a preset's config) to polyrank_rank_wallets to reproduce that board, or edit it. A goal `banner` is a measured caveat to show with the board. Free, no key.

Your saved strategies, newest first, each with its state and its latest backtest's headline (per $10 copied, copies; SIMULATED). `status` lists only one state: draft, backtested (tested), paper (paper trading), promotable (passed the paper gate), live, archived. Needs POLYRANK_API_KEY.

Rank every Polymarket wallet with your own composite — exactly what the Ranking Builder runs (POST /v1/rankings/custom). weights: metric id → weight (or {weight, window}); any of the 84 catalog metrics at any window it exists at (polyrank_get_metric_windows), plus copy-engine (sk_score_14d) and entry-timing ids at lifetime. filters: min_trades, min_resolved, min_inband_n_30d (the in-band positions behind inband_return_30d: a sort by engine:inband_return_30d applies 10 unless you set it, 1 = every measured wallet; the floor that ran is in applied_filters), min_volume_usdc, min_realized_pnl(_net_fees), min_win_rate_pct, max_roi_pct, active_within_days/hours, categories, exclude_bonders, skill_gates [{metric,min_pctile,window}], metric_filters [{metric,min,max,window}], copy_engine {sleeve}, timing {sub,bucket,window,min_n}, cluster_policy, copy_placeable, smart_money_tags_any_of, follower_count_max … (the server rejects anything it cannot apply, with the reason). A HISTORY BOARD (a Strategy Lab history ranking's latest seat) is filters {history_board: {board}} with board one of underdog-specialists | copier-consensus | predictors-early-underdog | sports-closing-line and NO weights: it is ranked by the seat's own order and served as that preset board; only active_within_days, active_within_hours and best_category may narrow it (window_days, score, min_positions, one_per_operator and other keys are not accepted there), plus limit, offset, sort_by, sort_dir, include_breakdown, include_verdict, extra_metrics, extra_engine_metrics, dedupe_clusters. as_of=YYYY-MM-DD ranks the board as it stood that day (lifetime snapshot metrics only — refused with the reason otherwise, never answered live). To reproduce a Builder goal, pass its `request` from polyrank_list_ranking_templates as `request`. Needs POLYRANK_API_KEY (a plan with the Builder).

Resolve an opaque masked id (tid) to the underlying proxy wallet address. Requires a Polyrank API key (pk_live_… / pk_test_…): set POLYRANK_API_KEY. The MCP sends it as a Bearer token and the API key-auth accepts it — no browser session needed. Then use the resolved wallet with polyrank_get_trader_skill / polyrank_get_trader_calibration.

Uses one of the plan's daily backtests: ask the user before calling, then pass confirm: true. Queue a backtest of a saved strategy (strategy_id) or an unsaved spec over [from, to) (ISO dates, at most 366 days), optionally with explicit re-rank cuts. Answers with the queued run; poll polyrank_get_backtest. Results are SIMULATED (each report names its fill model and measured optimism). Counts against your plan's daily backtests. Needs POLYRANK_API_KEY.

Writes to the user's Lab: ask the user before calling, then pass confirm: true. Start paper trading a saved strategy: from now on every signal of its wallets is scored against the real order book (no orders, no keys, no money). One active run per strategy. Needs POLYRANK_API_KEY (plan feature paper_trading).

Writes to the user's Lab: ask the user before calling, then pass confirm: true. Rename a saved strategy and/or replace its strategy spec (a changed spec makes it a draft again: its earlier backtests stay, tested on the old rules). The server validates the spec and answers with the reason when it refuses. Needs POLYRANK_API_KEY.