此 MCP 可以做什么
Retrieves USPTO patent application and grant records, prosecution events, and recorded assignment histories.
工具
输入模式
{'type': 'object', 'examples': [{'entity': 'Tesla'}], 'required': ['entity'], 'properties': {'entity': {'type': 'string', 'description': 'The thing to ask about. Brand/business name, product name, person, or topic. E.g. "Pipeworx", "OpenInvoice", "Acme Corp pricing".'}, 'models': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Which models to probe. Supported: "workers-ai" (free default), "anthropic" (requires _apiKey). Omit for just workers-ai.'}, '_apiKey': {'type': 'string', 'description': 'Optional Anthropic API key (sk-ant-...) â\x80\x94 only needed if "anthropic" is in models. Passed straight through to api.anthropic.com.'}, 'context': {'type': 'string', 'description': 'Optional: a phrase locating the entity (e.g. "Boston restaurant", "B2B SaaS"). Helps disambiguate common names.'}}}
输入模式
{'type': 'object', 'examples': [{'question': "What was Apple's revenue in 2024?"}, {'question': 'Any recent SEC filings for $NVDA?'}, {'question': 'Current price of bitcoin'}], 'required': ['question'], 'properties': {'q': {'type': 'string', 'description': 'Alias for question.'}, 'ask': {'type': 'string', 'description': 'Alias for question.'}, 'text': {'type': 'string', 'description': 'Alias for question.'}, 'input': {'type': 'string', 'description': 'Alias for question.'}, 'query': {'type': 'string', 'description': 'Alias for question.'}, 'prompt': {'type': 'string', 'description': 'Alias for question.'}, 'message': {'type': 'string', 'description': 'Alias for question.'}, 'question': {'type': 'string', 'description': 'Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.'}}}
输入模式
{'type': 'object', 'examples': [{'question': 'What is the current US unemployment rate?'}], 'required': ['question'], 'properties': {'q': {'type': 'string', 'description': 'Alias for question.'}, 'ask': {'type': 'string', 'description': 'Alias for question.'}, 'text': {'type': 'string', 'description': 'Alias for question.'}, 'input': {'type': 'string', 'description': 'Alias for question.'}, 'query': {'type': 'string', 'description': 'Alias for question.'}, 'prompt': {'type': 'string', 'description': 'Alias for question.'}, 'message': {'type': 'string', 'description': 'Alias for question.'}, 'question': {'type': 'string', 'description': 'Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.'}}}
输入模式
{'type': 'object', 'examples': [{'question': "What was Apple's fiscal 2023 revenue?"}], 'required': ['question'], 'properties': {'q': {'type': 'string', 'description': 'Alias for question.'}, 'ask': {'type': 'string', 'description': 'Alias for question.'}, 'text': {'type': 'string', 'description': 'Alias for question.'}, 'input': {'type': 'string', 'description': 'Alias for question.'}, 'query': {'type': 'string', 'description': 'Alias for question.'}, 'prompt': {'type': 'string', 'description': 'Alias for question.'}, 'message': {'type': 'string', 'description': 'Alias for question.'}, 'question': {'type': 'string', 'description': 'Your question in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.'}}}
输入模式
{'type': 'object', 'examples': [{'market': 'will-kristi-noem-win-the-2028-republican-presidential-nomination'}, {'market': 'https://polymarket.com/event/will-kristi-noem-win-the-2028-republican-presidential-nomination'}], 'required': ['market'], 'properties': {'depth': {'enum': ['quick', 'thorough'], 'type': 'string', 'description': 'quick = 2-3 evidence sources, thorough = full fan-out. Default thorough.'}, 'market': {'type': 'string', 'description': 'Polymarket slug ("will-kristi-noem-win-the-2028-republican-presidential-nomination"), full URL ("https://polymarket.com/event/..."), or question text ("Will Bitcoin hit $150k?"). Dated slugs stop resolving once they settle â\x80\x94 Polymarket de-indexes resolved markets â\x80\x94 so prefer an undated one.'}, 'include_raw': {'type': 'boolean', 'description': 'Default false. When false (recommended), FRED/FDA/GDELT/Federal-Register evidence is summarized to the few fields agents actually use â\x80\x94 keeps responses under ~20KB. Pass true to get full upstream payloads (50KB-500KB) when you need to recompute deltas, cite specific observations, or post-process.'}}}
输入模式
{'type': 'object', 'examples': [{'period': {'type': 'annual', 'fiscal_year': 2023}, 'company': 'AAPL', 'attribute': 'revenue'}], 'required': ['company', 'attribute', 'period'], 'properties': {'as_of': {'type': 'string', 'description': 'Past ISO timestamp with timezone. Replay the latest answer actually recorded by that instant; no invented history or live fallback.'}, 'basis': {'enum': ['consolidated'], 'type': 'string', 'description': 'Only "consolidated" in v1. Segment and product-level figures are XBRL-dimensioned and are not reachable through this contract at any concept.'}, 'period': {'type': 'object', 'required': ['type', 'fiscal_year'], 'properties': {'type': {'enum': ['annual', 'quarterly'], 'type': 'string', 'description': '"annual" = the full fiscal year. "quarterly" = ONE discrete quarter, never a year-to-date figure.'}, 'fiscal_year': {'type': 'number', 'description': "The FILER'S fiscal year â\x80\x94 the year the period ends in by their own calendar. Walmart's year ending 2026-01-31 is 2026."}, 'fiscal_quarter': {'type': 'number', 'description': '1-4. Required when type is "quarterly"; rejected when type is "annual".'}}, 'description': 'The reporting period, stated explicitly. There is no default and no "latest" â\x80\x94 that is the point of this tool.'}, 'company': {'type': 'string', 'description': 'Ticker ("AAPL"), 10-digit CIK ("0000320193"), or company name. A name that matches two filers equally well returns status "ambiguous" with both named rather than guessing â\x80\x94 pass a ticker or CIK to be certain.'}, 'max_age': {'type': 'number', 'maximum': 3155760000, 'minimum': 0, 'description': 'Maximum age in seconds of the upstream publication, not our fetch. Older or undated facts are withheld.'}, 'attribute': {'enum': ['revenue', 'net_income', 'cash'], 'type': 'string', 'description': 'Which figure. "revenue" = total consolidated revenue; "net_income" = net income (loss); "cash" = cash and cash equivalents at the period end.'}, 'freshness': {'enum': ['cached', 'fresh'], 'type': 'string', 'description': 'cached (default) permits an eligible stored answer; fresh requires an upstream refresh and never silently falls back to stale data.'}, 'restatement': {'enum': ['as_amended', 'as_originally_reported'], 'type': 'string', 'description': 'Default "as_amended" â\x80\x94 the latest filed figure for the period, with everything it superseded listed. "as_originally_reported" takes the first filing instead.'}, 'exclude_publishers': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Publisher ids forbidden for fact retrieval: sec, fmp, alphavantage. Case and surrounding whitespace are normalized; unknown ids are refused. Excluding sec currently leaves no eligible fact source and returns unavailable/sources_excluded with the selection reasons. Identity and fiscal-calendar lookups may still use SEC; no excluded financial concept is fetched.'}}}
输入模式
{'type': 'object', 'examples': [{'type': 'company', 'values': ['AAPL', 'MSFT']}], 'required': ['type', 'values'], 'properties': {'type': {'enum': ['company', 'drug'], 'type': 'string', 'description': 'Entity type: "company" or "drug".'}, 'values': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 5, 'minItems': 2, 'description': 'For company: 2â\x80\x935 tickers/CIKs (e.g., ["AAPL","MSFT"]). For drug: 2â\x80\x935 names (e.g., ["ozempic","mounjaro"]).'}}}
输入模式
{'type': 'object', 'examples': [{'depth': 'quick', 'question': 'What is the current US unemployment rate and how has it changed over the past year?'}], 'required': ['question'], 'properties': {'q': {'type': 'string', 'description': 'Alias for question.'}, 'ask': {'type': 'string', 'description': 'Alias for question.'}, 'text': {'type': 'string', 'description': 'Alias for question.'}, 'depth': {'enum': ['quick', 'standard', 'thorough'], 'type': 'string', 'description': 'How many facets to research in parallel: quick=3 (single hop), standard=3 (default; adds a gap-recovery hop that re-angles unanswered facets + a contradictions[] scan across findings), thorough=6 (paid; adds a full iterative hop that chases leads + recovers gaps, plus the contradictions[] scan).'}, 'input': {'type': 'string', 'description': 'Alias for question.'}, 'query': {'type': 'string', 'description': 'Alias for question.'}, 'prompt': {'type': 'string', 'description': 'Alias for question.'}, 'message': {'type': 'string', 'description': 'Alias for question.'}, 'question': {'type': 'string', 'description': 'The research question, in natural language. Broad/multi-part is fine â\x80\x94 decomposition is the point. Accepts query, q, prompt, text, input, ask, message as aliases.'}}}
输入模式
{'type': 'object', 'examples': [{'query': 'look up FDA drug approvals'}, {'query': 'analyze housing market trends'}], 'required': ['query'], 'properties': {'q': {'type': 'string', 'description': 'Alias for query.'}, 'task': {'type': 'string', 'description': 'Alias for query.'}, 'limit': {'type': 'number', 'description': 'Maximum number of tools to return (default 20, max 50)'}, 'query': {'type': 'string', 'description': 'Natural language description of what you want to do (e.g., "analyze housing market trends", "look up FDA drug approvals", "find trade data between countries"). Accepts task, q, description, search as aliases.'}, 'search': {'type': 'string', 'description': 'Alias for query.'}, 'description': {'type': 'string', 'description': 'Alias for query.'}}}
输入模式
{'type': 'object', 'examples': [{'type': 'company', 'value': 'AAPL'}], 'required': ['type', 'value'], 'properties': {'type': {'enum': ['company', 'ticker'], 'type': 'string', 'description': '"company" or "ticker" â\x80\x94 both are accepted and behave identically; `value` can be a ticker, CIK, or company name either way. person/place coming soon.'}, 'value': {'type': 'string', 'description': 'Ticker (e.g., "AAPL"), zero-padded CIK (e.g., "0000320193"), or company name (e.g., "Moderna") â\x80\x94 names resolve via SEC EDGAR company-name match.'}}}
输入模式
{'type': 'object', 'examples': [{'key': 'user_research_topic'}], 'required': ['key'], 'properties': {'k': {'type': 'string', 'description': 'Alias for key.'}, 'key': {'type': 'string', 'description': 'Memory key to delete. Accepts name, k, label as aliases.'}, 'name': {'type': 'string', 'description': 'Alias for key.'}, 'label': {'type': 'string', 'description': 'Alias for key.'}}}
输入模式
{'type': 'object', 'examples': [{'url': 'https://pipeworx.io'}], 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Full URL of the site to summarize, e.g. "https://example.com" or a specific landing page.'}, 'max_links': {'type': 'number', 'description': 'Maximum number of link entries to include (default 25, max 50).'}}}
输入模式
{'type': 'object', 'examples': [{'number': '16123456'}], 'required': ['number'], 'properties': {'number': {'type': 'string', 'description': 'Application number (digits only or with slashes). Examples: "16123456", "16/123,456".'}, '_apiKey': {'type': 'string', 'description': 'USPTO ODP API key. Get free at https://data.uspto.gov/myodp.'}}}
输出模式
{'type': 'object', 'required': ['patent_number', 'title', 'abstract', 'date', 'type', 'inventors', 'assignee_organization'], 'properties': {'date': {'type': ['string', 'null'], 'description': 'Patent filing date or null'}, 'type': {'type': ['string', 'null'], 'description': 'Patent type or null'}, 'title': {'type': 'string', 'description': 'Patent title'}, 'abstract': {'type': ['string', 'null'], 'description': 'Patent abstract or null'}, 'inventors': {'type': 'array', 'items': {'type': 'object', 'properties': {'city': {'type': ['string', 'null'], 'description': 'Inventor city or null'}, 'state': {'type': ['string', 'null'], 'description': 'Inventor state or null'}, 'last_name': {'type': ['string', 'null'], 'description': 'Inventor last name or null'}, 'first_name': {'type': ['string', 'null'], 'description': 'Inventor first name or null'}}}, 'description': 'List of inventors with details'}, 'patent_number': {'type': 'string', 'description': 'Patent number'}, 'assignee_organization': {'type': ['string', 'null'], 'description': 'Assignee organization name or null'}}}
输入模式
{'type': 'object', 'examples': [{'application_number': '15/000,001'}], 'required': ['application_number'], 'properties': {'_apiKey': {'type': 'string', 'description': 'USPTO ODP API key. Get free at https://data.uspto.gov/myodp.'}, 'application_number': {'type': 'string', 'description': 'US patent application number, digits only or formatted, e.g. "15/000,001".'}}}
输出模式
{'type': 'object', 'required': ['application_number', 'count', 'assignments', 'interpretation', 'source'], 'properties': {'count': {'type': 'number'}, 'source': {'type': 'string'}, 'assignments': {'type': 'array', 'items': {'type': 'object'}}, 'interpretation': {'type': 'string'}, 'application_number': {'type': 'string'}}}
输入模式
{'type': 'object', 'examples': [{'city': 'nyc'}, {'city': 'chicago'}, {'backtest_days': 14, 'series_ticker': 'KXHIGHNY'}], 'properties': {'city': {'type': 'string', 'description': 'City to price, e.g. "nyc", "chicago", "los angeles", "miami", "austin", "houston", "denver", "philadelphia". Defaults to nyc. Unmapped cities return known_cities[] rather than a wrong series.'}, 'date': {'type': 'string', 'description': 'Settlement date as YYYY-MM-DD. Defaults to the soonest open event. Daily weather markets open ~1-2 days ahead and close 05:00Z the next day.'}, 'market_type': {'type': 'string', 'description': '"high_temp" (default) | "precip". Precipitation markets return prices but no forecast_prob yet.'}, 'backtest_days': {'type': 'number', 'description': 'Run measurement mode over the last N settled days (max 60) instead of pricing today. Returns brier_market vs brier_forecast, the settlement-vs-forecast basis, and per-day detail. Both sides are scored at 12:00Z on each event day â\x80\x94 before the daily high and before resolution â\x80\x94 because a settled market prices the known outcome at close.'}, 'series_ticker': {'type': 'string', 'description': 'Explicit Kalshi series, e.g. "KXHIGHNY" or "KXHIGHTBOS" (Boston). Overrides `city`; use it for any of the 121 daily weather series not in the city list.'}}}
输入模式
{'type': 'object', 'required': [], 'properties': {'include_inactive': {'type': 'boolean', 'description': 'Include cancelled subscriptions in the response (default false).'}}}
输入模式
{'type': 'object', 'examples': [{'type': 'other', 'message': 'Fleet #2184 smoke test: verifying pipeworx_feedback example call returns non-empty.'}], 'properties': {'type': {'enum': ['bug', 'feature', 'data_gap', 'praise', 'other'], 'type': 'string', 'description': 'bug = something broke or returned wrong data. feature = a new tool or capability you wish existed. data_gap = data Pipeworx does not currently expose. praise = positive note. other = anything else.'}, 'context': {'type': 'object', 'properties': {'pack': {'type': 'string', 'description': 'Pack slug (e.g., "fred")'}, 'tool': {'type': 'string', 'description': 'Tool name (e.g., "fred_get_series")'}, 'vertical': {'type': 'string', 'description': 'Vertical (e.g., "housing")'}}, 'description': 'Optional structured context: which tool, pack, or vertical this relates to.'}, 'message': {'type': 'string', 'description': 'Your feedback in plain text. Be specific (which tool, what error, what data was missing). 1-2 sentences typical, 2000 chars max.'}, 'claim_token': {'type': 'string', 'description': 'Read the reply to a report you filed earlier: pass the `pwfb_â\x80¦` token that filing returned, with no other arguments. Returns the status and, once resolved, what actually changed.'}}}
输入模式
{'type': 'object', 'examples': [{'window': '7d'}], 'properties': {'window': {'enum': ['24h', '7d', '30d'], 'type': 'string', 'description': "24h (default) | 7d | 30d. Shorter windows surface what's hot right now; longer windows show steady-state demand."}}}
输入模式
{'type': 'object', 'examples': [{'topic': 'Fed rate decision'}], 'properties': {'event': {'type': 'string', 'description': 'Single-event mode (use this if you know the specific Polymarket event): event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k". Full Polymarket URLs also accepted.'}, 'topic': {'type': 'string', 'description': 'Cross-event mode (use this if you want to scan related events across the platform): a topic or seed question like "Fed rate decision" or "Strait of Hormuz traffic returns to normal". Tool searches Polymarket for related events and checks monotonicity across them.'}}}
输入模式
{'type': 'object', 'examples': [{'limit': 5, 'window': '1wk'}], 'properties': {'limit': {'type': 'number', 'description': 'Top N edges to return after ranking. Default 10, max 25.'}, 'window': {'enum': ['24hr', '1wk', '1mo'], 'type': 'string', 'description': 'Polymarket volume window to filter markets. Default 1wk.'}, 'min_kelly': {'type': 'number', 'description': 'Minimum half-Kelly fraction (as decimal, e.g. 0.005 = 0.5% of bankroll) to include single-leg opportunities. Default 0 (no filter). Skips opportunities that are too small to bet sensibly even if the edge is large.'}, 'min_edge_pp': {'type': 'number', 'description': "Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage and Polymarket's own taker fee."}, 'slippage_pp': {'type': 'number', 'description': "Assumed execution slippage in percentage points per leg (default 0.3), for bid/ask + thin depth cost that a last-trade price does not show. Subtracted from raw |edge| before ranking and Kelly sizing, ON TOP OF Polymarket's own taker fee â\x80\x94 which is NOT zero (rate 0.04-0.07 depending on category, read off each market's own published fee schedule; see fees_pp_applied on every row and fees.ts for the full schedule). Bump slippage for very thin partitions; drop to 0 if you have a smarter fill model â\x80\x94 the fee still applies regardless."}, 'max_spread_pp': {'type': 'number', 'description': 'Tradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books â\x80\x94 anything wider eats most plausible edges.'}, 'min_liquidity': {'type': 'number', 'description': 'Tradeable-edge filter. Minimum $ liquidity on the representative market (or for partition_overround, on at least one top_leg). Default 0 (no filter). Set to 5000 to drop thin-book opportunities where executing the edge would walk the book past breakeven.'}, 'category_filter': {'type': 'string', 'description': 'Comma-separated list to restrict the output: "model_driven" (crypto_price + news_momentum), "structural_arbitrage" (partition_overround), "concentrated_longshot". Combine like "model_driven,structural_arbitrage". Default: all.'}, 'min_partition_leg_kelly': {'type': 'number', 'description': "Minimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at the parent level by design (basket trades don't compose to single-leg Kelly), so min_kelly never filters them â\x80\x94 this knob applies to the per-leg Kelly inside top_legs instead. Use to suppress thin partitions whose individual leg edges aren't worth the per-leg slippage cost."}}}
输入模式
{'type': 'object', 'examples': [{'days': 14, 'window': '1wk'}], 'properties': {'days': {'type': 'number', 'description': 'Lookback in days (default 14, clamp 2-30).'}, 'window': {'type': 'string', 'description': 'Which polymarket_edges window family to read snapshots for: 24hr | 1wk | 1mo (default 1wk).'}}}
输入模式
{'type': 'object', 'examples': [{'side': 'buy_yes', 'market': 'will-the-fed-increase-interest-rates-by-25-bps-after-the-december-2026-meeting-20260729232808636', 'size_usd': 1000}], 'properties': {'side': {'type': 'string', 'description': 'Single-market: buy_yes | sell_yes | buy_no | sell_no (default buy_yes). Basket: sell_yes | buy_yes (default auto â\x80\x94 sell if partition sum > 1, buy if < 1).'}, 'event': {'type': 'string', 'description': 'Basket mode: event slug or full polymarket.com URL â\x80\x94 checks every leg of the partition.'}, 'market': {'type': 'string', 'description': 'Single-market mode: market slug or full polymarket.com URL.'}, 'size_usd': {'type': 'number', 'description': 'Single-market: USD to spend (buys) or target proceeds (sells). Basket: settlement notional â\x80\x94 shares per leg, each paying $1 at resolution. Default 1000, clamp 10â\x80\x931,000,000.'}}}
输入模式
{'type': 'object', 'examples': [{'topic': 'fed'}, {'topic': 'btc'}, {'topic': 'bitcoin'}, {'topic': 'fed rate decision'}], 'properties': {'topic': {'type': 'string', 'description': 'Subject to compare. Canonical keys: fed | btc | eth | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president â\x80\x94 but aliases and keywords resolve too ("bitcoin", "fed rate decision", "ethereum", "inflation", "s&p 500", "us recession", "next pope", "2028 election"). Check resolution.topic_matched_by in the response: "exact"/"alias" is a curated pairing, "phrase"/"token" is a keyword guess.'}, 'kalshi_event_ticker': {'type': 'string', 'description': 'Explicit Kalshi event ticker, e.g. "KXFED-26OCT". Overrides the topic-mapped Kalshi side.'}, 'polymarket_event_slug': {'type': 'string', 'description': 'Explicit Polymarket event slug, e.g. "fed-decision-in-june-825". Overrides the topic-mapped Polymarket side.'}}}
输入模式
{'type': 'object', 'examples': [{'key': 'user_research_topic'}, {}], 'required': [], 'properties': {'k': {'type': 'string', 'description': 'Alias for key.'}, 'key': {'type': 'string', 'description': 'Memory key to retrieve (omit to list all keys). Accepts name, k, label as aliases.'}, 'name': {'type': 'string', 'description': 'Alias for key.'}, 'label': {'type': 'string', 'description': 'Alias for key.'}}}
输入模式
{'type': 'object', 'required': [], 'properties': {'type': {'type': 'string', 'description': 'Optional â\x80\x94 filter to one subscription type.'}, 'limit': {'type': 'number', 'description': 'Max events to return (1-200, default 50).'}, 'since': {'type': 'string', 'description': 'Optional ISO timestamp â\x80\x94 return events fired_at >= this time.'}, 'mark_read': {'type': 'boolean', 'description': 'Flag the returned events read in the same call (default false).'}, 'unread_only': {'type': 'boolean', 'description': 'Return only events where read_at is null (default false).'}}}
输入模式
{'type': 'object', 'examples': [{'type': 'company', 'since': '30d', 'value': 'AAPL'}], 'required': ['type', 'value', 'since'], 'properties': {'type': {'enum': ['company'], 'type': 'string', 'description': 'Entity type. Only "company" supported today.'}, 'since': {'type': 'string', 'description': 'Window start â\x80\x94 ISO date ("2026-04-01") or relative ("7d", "30d", "3m", "1y"). Use "30d" or "1m" for typical monitoring.'}, 'value': {'type': 'string', 'description': 'Ticker (e.g., "AAPL") or zero-padded CIK (e.g., "0000320193").'}}}
输入模式
{'type': 'object', 'examples': [{'hours': 72}, {'hours': 100, 'categories': 'econ,fed'}], 'properties': {'hours': {'type': 'number', 'description': 'Look-ahead window in hours from now. Default 48. Capped at 720 (30 days) â\x80\x94 econ/fed releases are dated weeks apart, so a short window is often empty; widen rather than assume nothing is scheduled.'}, 'categories': {'type': 'string', 'description': 'Comma or space separated subset of econ|fed|fda|sec|court, or "all" (default). E.g. "econ,fed" or "fda".'}}}
输出模式
{'type': 'object', 'properties': {'as_of': {'type': 'string'}, 'notes': {'type': 'array', 'items': {'type': 'string'}}, 'window': {'type': 'object', 'properties': {'hours': {'type': 'number'}, 'since': {'type': 'string'}, 'until': {'type': 'string'}}}, 'releases': {'type': 'array', 'items': {'type': 'object', 'properties': {'markets': {'type': 'array', 'items': {'type': 'object', 'properties': {'price': {'type': ['number', 'null']}, 'venue': {'enum': ['kalshi', 'polymarket'], 'type': 'string'}, 'volume': {'type': ['number', 'null']}, 'question': {'type': 'string'}, 'matched_by': {'type': 'string'}, 'slug_or_ticker': {'type': 'string'}, 'hours_to_release': {'type': ['number', 'null']}, 'resolves_on_this_release': {'enum': ['true', 'likely', 'unclear'], 'type': 'string'}}}}, 'release': {'type': 'object', 'properties': {'name': {'type': 'string'}, 'category': {'enum': ['econ', 'fed', 'fda', 'sec', 'court'], 'type': 'string'}, 'date_only': {'type': 'boolean'}, 'source_pack': {'type': 'string'}, 'source_tool': {'type': 'string'}, 'time_source': {'type': 'string'}, 'scheduled_at': {'type': ['object', 'null'], 'properties': {'et': {'type': 'string'}, 'utc': {'type': 'string'}}}, 'hours_to_release': {'type': ['number', 'null']}, 'what_it_publishes': {'type': 'string'}}}}}}, 'categories': {'type': 'array', 'items': {'type': 'string'}}, 'release_count': {'type': 'number'}, 'releases_with_matched_markets': {'type': 'number'}}}
输入模式
{'type': 'object', 'examples': [{'key': 'target_ticker', 'value': 'AAPL'}], 'required': ['key', 'value'], 'properties': {'k': {'type': 'string', 'description': 'Alias for key.'}, 'v': {'type': 'string', 'description': 'Alias for value.'}, 'key': {'type': 'string', 'description': 'Memory key (e.g., "subject_property", "target_ticker", "user_preference"). Accepts name, k, label as aliases.'}, 'data': {'type': 'string', 'description': 'Alias for value.'}, 'name': {'type': 'string', 'description': 'Alias for key.'}, 'text': {'type': 'string', 'description': 'Alias for value.'}, 'label': {'type': 'string', 'description': 'Alias for key.'}, 'value': {'type': 'string', 'description': 'Value to store (any text â\x80\x94 findings, addresses, preferences, notes). Accepts content, text, data, v as aliases; a non-string value is stored as JSON.'}, 'content': {'type': 'string', 'description': 'Alias for value.'}}}
输入模式
{'type': 'object', 'examples': [{'venue': 'polymarket', 'market': 'bitcoin-above-70k-on-september-13-2026'}, {'venue': 'kalshi', 'market': 'KXBTCD-26SEP1317'}], 'required': ['venue', 'market'], 'properties': {'venue': {'enum': ['polymarket', 'kalshi'], 'type': 'string', 'description': 'Which venue to fetch the market from.'}, 'market': {'type': 'string', 'description': 'Polymarket market slug or URL, OR a Kalshi market ticker (preferred) or event ticker (falls back to a representative market under that event).'}}}
输入模式
{'type': 'object', 'examples': [{'a': {'venue': 'polymarket', 'market': 'bitcoin-above-70k-on-september-13-2026'}, 'b': {'venue': 'kalshi', 'market': 'KXBTCD-26SEP1317'}}], 'required': ['a', 'b'], 'properties': {'a': {'type': 'object', 'required': ['venue', 'market'], 'properties': {'venue': {'enum': ['polymarket', 'kalshi'], 'type': 'string'}, 'market': {'type': 'string'}}, 'description': 'First market to compare.'}, 'b': {'type': 'object', 'required': ['venue', 'market'], 'properties': {'venue': {'enum': ['polymarket', 'kalshi'], 'type': 'string'}, 'market': {'type': 'string'}}, 'description': 'Second market to compare.'}}}
输入模式
{'type': 'object', 'examples': [{'type': 'company', 'value': 'AAPL'}], 'required': ['type', 'value'], 'properties': {'type': {'enum': ['company', 'drug'], 'type': 'string', 'description': 'Entity type: "company" or "drug".'}, 'value': {'type': 'string', 'description': 'For company: ticker (AAPL), CIK (0000320193), or name. For drug: brand or generic name (e.g., "ozempic", "metformin"). Pass the ENTITY NAME ONLY â\x80\x94 for a bond that is the ISSUER exactly as printed ("NEW YORK ST DORM AUTH"), never the question\'s full noun phrase ("NEW YORK ST DORM AUTH revenue bonds"): the FIGI lookup matches instrument names, so trailing security-class words match nothing.'}}}
输入模式
{'type': 'object', 'examples': [{'entities': ['Pipeworx', 'Zapier']}], 'required': ['entities'], 'properties': {'models': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Which models to probe. Supported: "workers-ai" (free default), "anthropic" (requires _apiKey). Omit for just workers-ai.'}, '_apiKey': {'type': 'string', 'description': 'Optional Anthropic API key â\x80\x94 only if "anthropic" is in models. Passed to api.anthropic.com per probe.'}, 'context': {'type': 'string', 'description': 'Optional shared context applied to every probe (e.g. "B2B SaaS", "Boston restaurant"). Disambiguates common names.'}, 'entities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Array of 2-8 entities to compare (brand/business/product names). First entry treated as the "subject" for narrative; rest are competitors.'}}}
输入模式
{'type': 'object', 'examples': [{'package': 'left-pad'}], 'required': ['package'], 'properties': {'package': {'type': 'string', 'description': 'npm package name. Scoped packages (e.g. "@types/node") are accepted.'}, 'version': {'type': 'string', 'description': 'Specific version to check (e.g., "18.3.1"). Defaults to the latest published version when omitted.'}}}
输入模式
{'type': 'object', 'examples': [{'query': 'Smith'}, {'query': 'Johnson'}], 'required': ['query'], 'properties': {'limit': {'type': 'number', 'description': 'Number of results to return (default 10). USPTO caps every search at 25 records, so values above 25 have no effect â\x80\x94 use the filters to narrow instead.'}, 'query': {'type': 'string', 'description': 'Inventor last name to search for (case-insensitive). Examples: "Hinton", "Bengio".'}, '_apiKey': {'type': 'string', 'description': 'USPTO ODP API key. Get free at https://data.uspto.gov/myodp.'}}}
输出模式
{'type': 'object', 'required': ['query', 'total_results', 'returned', 'inventors'], 'properties': {'query': {'type': 'string', 'description': 'The search query used'}, 'returned': {'type': 'number', 'description': 'Number of inventors in this response'}, 'inventors': {'type': 'array', 'items': {'type': 'object', 'properties': {'city': {'type': ['string', 'null'], 'description': 'Inventor city or null'}, 'state': {'type': ['string', 'null'], 'description': 'Inventor state or null'}, 'last_name': {'type': ['string', 'null'], 'description': 'Inventor last name or null'}, 'first_name': {'type': ['string', 'null'], 'description': 'Inventor first name or null'}, 'patent_numbers': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Patent numbers associated with inventor'}}}, 'description': 'List of inventor details'}, 'total_results': {'type': 'number', 'description': 'Total number of matching inventors'}}}
输入模式
{'type': 'object', 'examples': [{'query': '"cell-free RNA"', 'filed_after': '2023-09-25', 'filed_before': '2026-09-25'}, {'query': 'machine learning neural networks'}, {'query': 'blockchain cryptocurrency'}, {'applicant': 'APPLE INC.'}, {'query': 'neural', 'inventor': 'Hinton'}], 'properties': {'limit': {'type': 'number', 'description': 'Number of results to return (default 10). USPTO caps every search at 25 records, so values above 25 have no effect â\x80\x94 use the filters to narrow instead.'}, 'query': {'type': 'string', 'description': 'Free-text keywords. Every term must appear (they are AND-ed), so add words to narrow and remove words to widen. Wrap words in double quotes to require them adjacent: `"machine learning" model` needs the exact phrase plus the word model. Examples: "lithium battery", "crispr", "neural network". Pass "*" if you only want to filter by applicant/date with no keyword constraint. If several quoted phrases ANDed together match nothing, the tool retries once with them OR\'d instead (see `broadened` in the response) rather than returning a bare zero.'}, 'title': {'type': 'string', 'description': 'Optional. Words that must appear in the invention title, which narrows far harder than `query` does since `query` searches the whole record. Example: "solid state battery".'}, 'number': {'type': 'string', 'description': 'Optional. A specific US application number, digits only or formatted â\x80\x94 "16123456" or "16/123,456". Accepted synonyms: `application_number`, `patent_number`.'}, '_apiKey': {'type': 'string', 'description': 'USPTO ODP API key. Get free at https://data.uspto.gov/myodp. Falls back to platform key if configured.'}, 'inventor': {'type': 'string', 'description': 'Optional. Inventor name as recorded on the filing; a last name matches most reliably. Examples: "Hinton", "Bengio". Accepted synonyms: `inventor_name`, `author`.'}, 'applicant': {'type': 'string', 'description': 'Optional. Company applicant name as it appears on the USPTO filing. **Must include the exact corporate suffix** the company uses (PBC / Inc. / LLC / Corporation / Co. / NV / AG / KK). A wrong or missing suffix matches nothing â\x80\x94 "Apple" returns zero where "APPLE INC." returns hundreds. Examples: "Anthropic, PBC" (not "Anthropic Inc."), "Apple Inc." (not "Apple"), "Alphabet Inc." (not "Google"), "Meta Platforms, Inc." (not "Facebook"), "Microsoft Corporation" (not "Microsoft Corp."). If you get zero results plus a `warning` field, the name form is wrong rather than the company being absent â\x80\x94 retry with a different corporate form.'}, 'filed_after': {'type': 'string', 'description': 'Optional. Filter to patents FILED on/after this date (ISO YYYY-MM-DD). Use this for "who has filed / applied for patents on X (recently / in the last N years)" â\x80\x94 it covers both pending applications and already-granted patents, so it is the right bound even when the question also says "recent". Do NOT substitute `granted_after` for a filing-activity question: grant lags filing by 2+ years, so a recent filing window under `granted_after` typically returns zero even when filing activity is real.'}, 'filed_before': {'type': 'string', 'description': 'Optional. Filter to patents FILED on/before this date (ISO YYYY-MM-DD).'}, 'granted_after': {'type': 'string', 'description': 'Optional. Filter to patents GRANTED (issued) on/after this date (ISO YYYY-MM-DD) â\x80\x94 use ONLY when the question explicitly says GRANTED / ISSUED / APPROVED, not for a plain "recent patents" or "who has filed" question (use `filed_after` for those â\x80\x94 see its description). Accepted synonym: `issued_after`.'}, 'granted_before': {'type': 'string', 'description': 'Optional. Filter to patents GRANTED (issued) on/before this date (ISO YYYY-MM-DD). Accepted synonym: `issued_before`.'}}}
输出模式
{'type': 'object', 'required': ['query', 'filters', 'total', 'returned', 'results', 'patents'], 'properties': {'note': {'type': 'string', 'description': 'Present when total exceeds the returned records â\x80\x94 explains the 25-record ODP page cap'}, 'query': {'type': 'string', 'description': 'The composed ODP query string actually sent'}, 'total': {'type': 'number', 'description': 'Total number of matching applications (USPTO ODP returns at most 25 records per search regardless of limit)'}, 'filters': {'type': 'object', 'properties': {'applicant': {'type': ['string', 'null']}, 'filed_after': {'type': ['string', 'null']}, 'filed_before': {'type': ['string', 'null']}, 'granted_after': {'type': ['string', 'null']}, 'granted_before': {'type': ['string', 'null']}}, 'description': 'Echo of the structured filters applied; each is null when unused'}, 'patents': {'type': 'array', 'items': {'type': 'object', 'required': ['patent_number', 'title', 'date', 'inventors', 'assignee_organization'], 'properties': {'date': {'type': ['string', 'null'], 'description': 'Patent filing date or null'}, 'title': {'type': 'string', 'description': 'Patent title'}, 'inventors': {'type': 'array', 'items': {'type': 'object', 'properties': {'last_name': {'type': ['string', 'null'], 'description': 'Inventor last name or null'}, 'first_name': {'type': ['string', 'null'], 'description': 'Inventor first name or null'}}}, 'description': 'List of inventors'}, 'patent_number': {'type': 'string', 'description': 'Patent number'}, 'assignee_organization': {'type': ['string', 'null'], 'description': 'Assignee organization name or null'}}}, 'description': 'Same records with full ODP fields'}, 'results': {'type': 'array', 'items': {'type': 'object'}, 'description': 'Back-compat summary shape (title, number, dates, applicant)'}, 'warning': {'type': 'string', 'description': 'Present when an applicant filter matched nothing â\x80\x94 ODP matches the corporate name literally ("APPLE INC." not "Apple")'}, 'returned': {'type': 'number', 'description': 'Number of records in this response'}}}
输入模式
{'type': 'object', 'examples': [{'text': 'Apple Inc. reported fiscal 2023 revenue of $383.285 billion, driven by strong iPhone and Services growth. Net income was $96.995 billion. The company faced supply-chain risk in China during the quarter.', 'query': 'supply-chain risk'}], 'required': ['text', 'query'], 'properties': {'text': {'type': 'string', 'description': 'The document text to search inside (max ~200K chars).'}, 'limit': {'type': 'number', 'description': 'Max passages to return (1-20, default 5).'}, 'query': {'type': 'string', 'description': 'Natural-language query â\x80\x94 what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin".'}}}
输入模式
{'type': 'object', 'required': ['type', 'params'], 'properties': {'type': {'enum': ['sec_8k', 'polymarket_edge', 'fred_series', 'patent_grant', 'clinical_trial'], 'type': 'string', 'description': 'Subscription type.'}, 'params': {'type': 'object', 'description': 'Type-specific filter. sec_8k: {ticker:"AAPL", items?:["5.02","1.01"]}. polymarket_edge: {topic:"fed", min_spread_bps?:500}. fred_series: {series_id:"UNRATE"}. patent_grant: {applicant:"Apple Inc."}. clinical_trial: {sponsor?:"Pfizer", condition?:"lung cancer", phase?:"PHASE3"} (sponsor or condition required).'}, 'delivery': {'type': 'object', 'properties': {'sms': {'type': 'string', 'description': 'E.164 phone number, e.g. "+15551234567". Must match the account\'s verified phone.'}, 'email': {'type': 'string', 'description': 'Email address to deliver alerts to. Validated against a standard pattern.'}, 'webhook': {'type': 'string', 'description': 'HTTPS URL to POST fired events to. https only; localhost/private hosts rejected. Signing secret returned once at subscribe time.'}}, 'description': 'Optional delivery channels in addition to the always-on persistent feed. {email:"you@x.com"} sends a templated alert per fired event. {sms:"+15551234567"} sends an SMS per event â\x80\x94 must match the verified phone on the caller\'s account (verify at https://pipeworx.io/account first; 10/day cap). {webhook:"https://..."} POSTs each event JSON to your endpoint, HMAC-signed â\x80\x94 the response includes delivery.webhook_secret (whsec_â\x80¦) ONCE; verify X-Pipeworx-Signature = sha256 HMAC of "<X-Pipeworx-Timestamp>.<raw body>". Auto-disabled after 10 consecutive failing runs.'}}}
输入模式
{'type': 'object', 'examples': [{'topic': 'finance'}], 'properties': {'topic': {'type': 'string', 'description': 'Optional focus area: finance | pharma | economics | real-estate | betting | weather | government | science | news. Omit for a cross-category spread.'}}}
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Subscription id (uuid) returned by subscribe.'}}}
输入模式
{'type': 'object', 'examples': [{'claim': "Apple's fiscal 2023 revenue was $383 billion"}], 'required': ['claim'], 'properties': {'claim': {'type': 'string', 'description': 'Natural-language factual claim, e.g., "Apple\'s FY2024 revenue was $400 billion" or "Microsoft made about $100B in profit last year".'}, 'tolerance_pct': {'type': 'number', 'description': 'Max percent deviation still graded approximately_correct (0.5â\x80\x9350). Overrides the tolerance implied by the claim wording â\x80\x94 set 1â\x80\x932 for hallucination detection where any material error must be refuted. Default: implied by wording, capped at 5.'}}}
近期工具变更
类似的 MCP 服务器
BNM Data Shop
Sells access to cached official reports, enforcement orders, regulatory documents, inspection records, and other public-source te…
Dados Abertos Senado BR MCP
Searches and retrieves Brazilian Federal Senate legislative, administrative, budgetary, contracting, speech, committee, and e-Cid…
OpenHelvetia Gateway
Provides sourced access to Swiss federal legislation and political data, including law metadata, versions, amendments, citations,…
GleanMark Trademark Search
Searches and analyzes USPTO trademark records, including conflicts, prosecution histories, TTAB proceedings, ownership chains, de…
editalmd
Searches Brazilian public procurement opportunities and documents, tracks deadlines and alerts, and supports tender document acce…
DataNexus MCP
Enables public-data research across domains, patents, government contracts, nonprofits, compliance registries, and software secur…
agentdata-nl
Provides paid company, insolvency, sanctions, regulatory, crypto-market, news, payment-counterparty, and structured web research …
FDA Data MCP
Searches and analyzes FDA data covering drugs, devices, facilities, inspections, recalls, approvals, shortages, enforcement, and …