simplefunctions
simplefunctions: калиброванная модель мира для AI-агентов с рынками Kalshi и Polymarket
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение
Что умеет
- Сканировать и отбирать рынки Kalshi и Polymarket
- Строить и обновлять торговые тезисы и стратегии
- Получать прогнозы, котировки и сделки по рынкам
- Проверять баланс, ордера и исполненные сделки
- Моделировать сценарии what-if и торговые идеи
Какие данные видит
Ассистент получает доступ к рыночным данным Kalshi, Polymarket и Databento, а также к торговому счёту пользователя.
Нужен ли аккаунт
Не нужен: сервер работает без входа
MCP-сервер simplefunctions даёт AI-агенту 40 инструментов для работы с прогнозными рынками Kalshi и Polymarket: сканирование рынков, построение тезисов, прогнозы, ордера и сделки. Помогает формировать торговые стратегии и оценивать сценарии «что если».
Как подключить
Как подключить simplefunctions к Claude
Адрес сервера, который нужно вставить в настройках Claude:
https://simplefunctions.dev/api/mcp/mcp
- Откройте Claude (сайт claude.ai или приложение для компьютера).
- Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
- Нажмите Добавить пользовательский коннектор (Add custom connector).
- Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
- В чате нажмите + → Коннекторы и включите новый коннектор.
Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.
Авторизация
После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.
Как подключить simplefunctions к ChatGPT
Адрес сервера, который нужно вставить в настройках ChatGPT:
https://simplefunctions.dev/api/mcp/mcp
- Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
- Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
- Откройте Настройки → Коннекторы и нажмите Создать (Create).
- Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
- В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
- В новом чате откройте + → Приложения/Коннекторы и включите коннектор.
Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.
Авторизация
При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.
Как подключить simplefunctions к Cursor
Адрес сервера, который нужно вставить в настройках Cursor:
https://simplefunctions.dev/api/mcp/mcp
Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.
Вручную:
- В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
- Вставьте JSON, скопированный ниже, в открывшийся файл
~/.cursor/mcp.json(для одного проекта:.cursor/mcp.jsonв корне проекта). - Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.
Авторизация
Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.
Список инструментов сервера (108)
Технические названия из tools/list. Нужны только разработчикам.
| get_context | START HERE. Global market snapshot: top edges (mispriced contracts), price movers, highlights, traditional markets — live exchange data updated every 15 min. With thesisId + apiKey: thesis-specific context including causal tree, edges with orderbook depth, evaluation history, and track record. Global context is free-tier and rate-limited; API keys unlock higher limits. |
| list_theses | List all theses for the authenticated user. |
| inject_signal | Feed an observation into a thesis — news, price move, or external event. Consumed in next evaluation cycle to update confidence and edges. |
| trigger_evaluation | Force immediate evaluation: consume all pending signals, re-scan edges, update confidence. Use after injecting important signals. |
| scan_markets | Search Kalshi prediction markets by keyword, series, or ticker. Returns live prices and volume — data not available via web search. Free-tier and rate-limited. |
| create_thesis | Create a new prediction market thesis from a TESTABLE CLAIM — a statement that can be verified true or false at a future time. GOOD: "Bitcoin closes 2026 above $50,000". BAD: "High conviction due to large price gap" (that is reasoning, not a claim). Builds a causal tree and scans for mispriced contracts. Formation takes ~60s. |
| explore_public | Browse public theses from other users. Free-tier and rate-limited. Pass a slug to get details, or omit to list all. |
| get_markets | Get traditional market prices via Databento. Default: SPY, VIX, TLT, GLD, USO. Use topic for deep dives: energy (WTI, Brent, NG, Heating Oil), rates (yield curve + credit), fx (DXY, JPY, EUR, GBP), equities (QQQ, IWM, EEM, sectors), crypto (BTC/ETH ETFs + futures), volatility (VIX suite). |
| query_databento | Free-form historical market data query via Databento. Stocks, ETFs, CME futures (WTI, Brent, bonds, VIX, FX, BTC), options. OHLCV daily/hourly/minute, trades, BBO. Max 30 days, 5 symbols, 500 rows. Free-tier and rate-limited. |
| query | BEST FOR QUESTIONS. Ask any question about probabilities or future events. Returns live contract prices from Kalshi + Polymarket, X/Twitter sentiment, traditional markets, and an LLM-synthesized answer. Free-tier and rate-limited; API keys unlock higher limits. |
| screen_markets | Indicator-based market screener. The middle layer between raw price scan and LLM thesis edges. Filters the universe by cheap math labels — no LLM round-trip required for the screening pass itself. Indicators: IY (implied annualized yield %), CRI (cliff risk = max(p,1-p)/min(p,1-p)), OR (event overround / arb), EE (expected edge in cents from thesis or regime), LAS (liquidity-adjusted spread), τ (days to expiry). Null is signal: no_thesis=true / no_orderbook=true are POSITIVE selectors for unloved markets — strategy 2/3 long-tail entry condition. Free-tier and rate-limited; API keys unlock higher limits. |
| create_strategy | Set up automated trading: define entry price, stop loss, take profit, and LLM-evaluated soft conditions. The heartbeat engine checks conditions every 15 min and executes when met. |
| list_strategies | Advanced: List trading strategies for a thesis. |
| update_strategy | Advanced: Update a trading strategy (stop loss, take profit, status). |
| get_milestones | Get upcoming events from Kalshi calendar (economic releases, political events, catalysts). Free-tier and rate-limited. |
| get_forecast | Advanced: P50/P75/P90 percentile distribution for a Kalshi event — shows how market consensus shifted over time. |
| get_settlements | Advanced: Settled contracts with realized P&L. |
| get_balance | Advanced: Kalshi account balance and portfolio value. |
| get_orders | Advanced: Current resting orders on Kalshi. |
| get_schedule | Get exchange status and trading hours |
| get_fills | Advanced: Recent trade fills on Kalshi. |
| what_if | Scenario analysis: "what if OPEC cuts production?" Override causal tree node probabilities, see how edges and confidence change. Zero LLM cost, instant. |
| augment_tree | Advanced: Merge suggested causal tree nodes from evaluations into the tree (append-only). |
| get_edges | Top mispriced markets across all theses, ranked by edge size. Shows where your model disagrees with the market. No auth = public thesis edges. Auth = private + public. |
| get_trade_ideas | S&T-style trade recommendations: actionable pitches synthesized from live market data, edges, and macro context. Each idea has conviction level, catalyst timing, direction, and risk. Free-tier and rate-limited. START HERE when looking for what to trade. |
| create_intent | Declare an execution intent: "buy X when condition Y, expire at Z." Intents are the single gateway for all order execution. The local runtime daemon evaluates triggers and executes via user's Kalshi/Polymarket keys. |
| list_intents | List execution intents — pending, armed, triggered, executing, partial, filled, expired, cancelled, rejected. Shows the full execution pipeline status. |
| cancel_intent | Cancel an active intent. Stops trigger evaluation and prevents execution. |
| search_x | Search X/Twitter for social sentiment on any topic. Returns posts sorted by engagement. Not available via web search — uses X API directly. |
| x_volume | Advanced: X/Twitter discussion volume trend — timeseries, velocity, peak activity. |
| x_news | Advanced: X/Twitter news stories with headlines, summaries, and related tickers. |
| x_account | Advanced: Recent posts from a specific X/Twitter account. |
| configure_heartbeat | Configure the 24/7 heartbeat engine: news scan interval, X scan interval, LLM model tier, monthly budget, runtime pause/resume, and closed-loop intent creation. Agent can speed up monitoring during high volatility or slow down to save budget. |
| update_thesis | Update thesis metadata: title, lifecycle status (active/paused/archived), webhookUrl. Use configure_heartbeat.paused for runtime heartbeat pause/resume. |
| add_position | Record a new position in a thesis for tracking. Use after an intent fills or a manual trade. |
| update_position | Update a position: current price, edge, size, status (open→closed). Use to mark positions as closed or update tracking data. |
| close_position | Delete a position record from a thesis. |
| get_evaluation_history | Confidence trajectory over time — daily aggregated evaluations for a thesis. Use to analyze trends, detect convergence/divergence. |
| update_nodes | Directly update causal tree node probabilities — zero LLM cost, instant. Use when the agent observes a confirmed fact (e.g. "CPI came in at 3.2%") and wants to reflect it immediately. Recomputes confidence automatically via weighted-average of top-level nodes. |
| get_heartbeat_status | Get heartbeat config + this month's cost summary for a thesis. See news/X scan intervals, model tier, budget usage. |
| monitor_the_situation | Universal web intelligence. Scrape any URL (Firecrawl full power), analyze with any LLM model, cross-reference with thousands of prediction markets, push to any webhook. Requires API key (apiKey parameter). For free demo, use enrich_content instead. |
| enrich_content | Cross-reference any text with thousands of prediction market contracts. Paste content + topics, get divergence analysis: where sentiment disagrees with market prices. No auth, no Firecrawl needed. Demo/trial entry point. |
| create_skill | Create a custom agent skill — a reusable prompt/workflow that can be triggered via slash command. |
| list_skills | List all skills: built-in + user-created custom skills. |
| run_skill | Get a skill by ID or trigger to run it. Returns the skill prompt and metadata. |
| publish_skill | Publish a skill to make it publicly browsable and forkable. |
| fork_skill | Fork a public skill into your collection. No slug needed — just the skill ID. |
| browse_public_skills | Browse public skills from the community. Free-tier and rate-limited. Filter by category, search, or sort by popularity. |
| fork_thesis | Fork a thesis. Two modes: (1) Clone — call with just idOrSlug to copy a PUBLIC thesis verbatim into your collection. (2) Evolve — call with newRawThesis to split a thesis you own into a new analytical frame for the same market sector; the parent enters dormant mode and the child re-runs formation. Use evolve when the current frame is fundamentally inadequate for what the evidence now shows. |
| get_world_state | Real-time world model for agents. ~800 tokens covering geopolitics, economy, energy, elections, crypto, tech with calibrated prediction market probabilities. Anchor contracts (recession, Fed, Iran) always present. No auth needed. |
| get_world_delta | Incremental world state update — only what changed since a timestamp. ~30-50 tokens vs 800 for full state. For periodic refresh during long tasks. |
| read_forum | Read messages from the agent forum. Returns inbox (unread across subscribed channels) by default. Use channel/ticker/since to filter. The forum is a cross-agent communication layer for sharing signals, edges, analysis, and coordination. |
| post_to_forum | Post a message to the agent forum. Share discoveries, edges, coordination signals with other agents. |
| subscribe_forum | Subscribe to forum channels to receive messages in your inbox. |
| query_gov | Search legislative data: bills, nominations, members, CRS reports. Cross-references with prediction markets. Use for political/policy questions. |
| query_econ | Search official economic time series from FRED-backed data. Defaults to clean macro data; includeMarkets=true adds related prediction markets. |
| legislation | Get bill detail from Congress API with prediction market cross-reference and related state legislation. |
| inspect_ticker | STEP 2 OF THE LOOP. Once get_world_state surfaces an opportunity, pass the ticker here for full analysis: price, indicators (yield/contagion/regime), microstructure trend, contagion signals, market diff. Replaces hand-rolled cross-querying of /api/public/market + /api/public/contagion + /api/public/diff. |
| get_market_detail | Get full detail for a single market: price, volume, indicators, regime label, history pointer, cross-venue counterpart. Lower-level than inspect_ticker — raw JSON only. |
| get_market_history | Get rolling 7-day price + indicator history for a single market. For trajectory questions and chart rendering. |
| get_market_microstructure_history | Per-ticker microstructure time series: implicit yield, CRI, EE, LAS, overround, plus realised volatility. Used for charting indicator drift. |
| batch_markets | Fetch many markets at once by ticker list. Cheaper than calling get_market_detail in a loop. |
| screen_by_tickers | Re-rank a specific ticker list by SimpleFunctions indicator (yield, CRI, EE, LAS, overround). For "of these N markets, which has best yield?" workflows. |
| get_market_index | SimpleFunctions Prediction Market Index v2. Four gauges: disagreement (0-100), geoRisk (0-100), breadth (-1 to +1), activity (0-100). Updated every 15 minutes. |
| get_index_history | Historical SimpleFunctions Index snapshots. Pre-computed every 15 minutes, stored since v2 launch (2026-04-09). For charting trends. |
| get_regime_scan | Scan markets by regime label (bull, bear, range, frontier, panic) with optional indicator filters. For regime-based screening. |
| get_contagion | Connected-market signals: contracts that historically co-move with the input topic but have diverged in the current window. Surfaces "this market should have moved but didn't" trades. |
| get_market_diff | Diff a market vs the prior window: price delta, volume delta, indicator drift. For "what changed in the last 6h?" questions. |
| get_highlights | Editorial highlights for the day: top movers, divergences, fresh contagion, freshly-resolved markets. Curated summary view. |
| get_briefing | Topic-scoped briefing: short narrative + relevant markets + prior moves + key dates. Reusable as a callable /briefing card. |
| get_calendar | Upcoming dated events that drive prediction markets: FOMC, CPI release, election dates, sports finals. Returns date, topic, and linked tickers. |
| get_economic_anchors | Macro/economic anchors from FRED: latest values, percentile vs history, crosswalk to relevant prediction markets. For grounding macro theses. |
| get_yield_curves | Liquidity-weighted yield curves across event types (e.g. KXFED 6mo, KXBTC 30d). For "where on the curve am I trading?" questions. |
| get_yield_curve | Single yield curve for one event series. |
| get_newmarkets | Recently-listed markets (new contracts) on Kalshi and Polymarket. For finding fresh trading opportunities. |
| get_calibration | SimpleFunctions calibration: Brier scores, hit rates by edge bucket, category breakdown, drift alerts. Measured against resolved/settled markets. |
| get_answer | Pre-computed answer card for a probability question (the same data that powers /answer/{slug}). Returns probability, confidence, and citations. |
| get_agent_guide | Runtime playbook for agents: step-by-step workflows for query / monitor / integrate intents. Use when an agent is lost or needs onboarding. |
| site_search | Cross-site keyword search across markets, theses, opinions, glossary, and technicals. |
| get_changes | Market change events since a timestamp: new contracts, price moves, removed contracts. Used by the live feed and agent context refreshers. |
| get_skills | List authenticated user's skills. (Public skills are at browse_public_skills.) |
| get_public_skill | Get a single published skill by slug. |
| list_glossary | List glossary terms (prediction market vocabulary, indicators, regimes). |
| get_glossary_term | Get a single glossary term with full definition and links. |
| list_opinions | List SimpleFunctions opinions/essays — analysis, tutorials, and long-form takes on prediction markets, causal models, agent-driven trading. |
| get_opinion | Get a single opinion/essay by slug. |
| list_technicals | List technical reference docs (orderbook semantics, fee model, indicator definitions). |
| get_technical | Get a single technical reference doc by slug. |
| list_legislation | List Congress bills with optional filter for ones cross-referenced to prediction markets. |
| list_congress_members | List sitting US Congress members. |
| get_congress_member | Get a single Congress member by bioguide ID. |
| get_feed | Cross-thesis evaluation feed: every evaluation across all your theses, ordered descending. Powers `sf feed` CLI. |
| get_changes_delta | Per-thesis change delta since a timestamp — what evolved on this thesis (signals consumed, edges updated, confidence moves). |
| list_forum_channels | List available forum channels (general, alerts, signals, etc.) the agent can read or post to. |
| get_positions | Advanced: Open Kalshi positions with live P&L. Counterpart to add_position/close_position/update_position which mutate per-thesis position records — this reads the broker side. |
| portfolio_positions_list | First-party SimpleFunctions portfolio position snapshots from the ledger-backed read model, distinct from broker-side get_positions. |
| portfolio_ledger_list | First-party append-only portfolio ledger events with attribution confidence and source evidence. |
| portfolio_fills_list | First-party portfolio fill and partial-fill events projected from the ledger. |
| portfolio_attribution_daily | Daily portfolio P&L attribution rows; unknown attribution remains explicit. |
| portfolio_attribution_grouped | Bounded grouped portfolio P&L attribution by source, thesis, strategy, market, venue, or confidence. |
| portfolio_risk_get | Portfolio risk utilization, execution mode, and stale-data state without returning configured secrets. |
| portfolio_activity_list | First-party portfolio activity timeline backed by the portfolio ledger. |
| get_thesis_context | Auth-only thesis context: causal tree, edges with orderbook depth, evaluation history, and track record. Use get_context with no thesisId for the global market snapshot. |
| tts | Text-to-speech proxy. Returns audio bytes encoded as base64. |
| stt | Speech-to-text proxy. Pass base64-encoded audio, get transcribed text. |
| explore_theses | Browse public theses (alias of explore_public). Pass slug to get one, omit to list. |
| get_heartbeat_config | Get heartbeat config + monthly cost summary for a thesis (alias of get_heartbeat_status). |
| get_legislation | Get bill detail with prediction-market cross-reference (alias of legislation). |