Tool search 164,478 tools · 10,067 live servers

Your first call when you do not know which x402 service exists for a job: it narrows a directory of 500+ listed services to candidates. Filter by free-text query, category, network, live status, and whether the last observed 402 envelope is signable by a standard x402 client; sort by newest, uptime, cheapest, or endpoints. Returns up to 100 compact summaries a page: price in decimal USD, uptime, status, verification. Then x402_get_service for the full record.

BM25 search over all 368 AINumbers ChainGraph chains. Returns ranked chains with their full recipe: ordered node sequence, deep-links, composer URL, and entry tool mcp_name. Agent flow: find_chain(query) → read recipe → call the listed node MCP tools in order, passing parent_hashes between steps. Task-shaped queries work well: "reserve composition recompute", "FR 2052a classification", "CCP margin replication", "SR 26-2 model validation benchmark", "litigation damages recompute", "evidence pack assembly".

Compatibility tool for older clients: search the Bullrun ETF universe and optionally bundle profile, recent prices, and latest holdings for an exact ticker. New clients should use search_etfs, get_etf_snapshot, and get_etf_holdings for smaller responses, structured output, quantitative filters, and explicit coverage metadata. Read-only.

Get OHLCV price history for a ticker — open/high/low/close/volume bars over a window, for charting, backtesting, and technical analysis. PAID: $0.01 USDC per query after a daily free allowance. On a 402, pay the returned Solana memo and re-call with the SAME args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

Get the option chain for a ticker — calls and puts with strike, last price, bid/ask, volume, open interest, and implied volatility, plus the available expiries. (Greeks are not provided by the source; IV/OI/volume are.) PAID: $0.02 USDC per query after a daily free allowance. On a 402, pay the returned Solana memo and re-call with the SAME args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

Screen the tracked large-cap universe by market cap, trailing P/E, dividend yield, and sector — returns matching stocks ranked by market cap. A raw market-data filter; for a ranked, fundamentals-driven screen pair this with financial-signals-mcp's composite_value_score. PAID: $0.01 USDC per query after a daily free allowance. On a 402, pay the returned Solana memo and re-call with the SAME args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

List GCP Billing BigQuery export credential records linked to this install.

Query normalized GCP Billing BigQuery export costs by day, service, project, and SKU. Returns compact totals only.

Query top GCP services by cost from the user's BigQuery billing export. Returns normalized service totals.

Purpose: Query paper-trading history with dynamic filters (action / P&L / time / symbol). Triggers (casual questions too): "what trades happened lately?", "최근 거래 내역 보여줘", "how did the BTC trades go?", "승률 어때?", "show me the trade log", "how many trades won this week?". When to call: past trade review, single-symbol post-mortem, win-rate audits. Prerequisites: none. Next steps: analyze_trades, market://{market_id}/signals/feedback. Caveats: paper-trading data only (not real money). limit capped at 1000. Args: market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted) limit: Max results (default 1000) action_filter: Filter by action (all, buy, sell) min_pnl: Min P&L % filter (e.g., -5.0) max_pnl: Max P&L % filter (e.g., 10.0) hours_back: Only trades within last N hours symbol: Filter by ticker symbol (e.g., "BTC", "AAPL"); case-insensitive Disclaimer: Information only, not investment advice.

Purpose: Query research signals with dynamic filters (symbol / interval / action / score / confidence). Triggers (casual questions too): "should I buy / sell X?", "살까 말까?", "good entry?", "what's the signal for BTC / AAPL / 삼성전자?", "is X bullish or bearish?", "any buy signals right now?". Returns a research signal + score (NOT an order or advice — always surface the disclaimer). Pair with get_latest_decisions to show what the system did. When to call: drilling into a specific signal slice; symbol-by-symbol scanning; any "should I trade X?" question about a live symbol. Prerequisites: market://{market_id}/signals/summary recommended for global view. Next steps: get_signal_detail, get_role_analysis. Caveats: When `symbol`/`coin` is omitted, the whole market is scanned in one consolidated query (2 newest rows per symbol, newest-first scan cap per interval). Args: market_id: Market ID (crypto, kr_stock, us_stock; aliases coin/kr/us accepted) symbol: Asset identifier to query (preferred; optional — targets a specific symbol DB) coin: Legacy alias of symbol (kept for backward compatibility) interval: Timeframe filter (15m, 30m, 240m, 1d, combined) action_filter: Action filter (buy, sell, hold) min_score: Minimum signal score threshold min_confidence: Minimum confidence threshold limit: Max results (default 500) hours_back: Only signals within last N hours (default 24) Disclaimer: Information only, not investment advice. Signals are research output, not orders.

Purpose: ChatGPT-connector-standard discovery search over OneQAZ's live surface — tools, resources, and the latest strong combined signals across crypto / kr_stock / us_stock. Returns result ids consumable by the `fetch` tool. Triggers: ChatGPT connectors and Deep Research call this automatically for any user query routed to OneQAZ ("bitcoin signal", "prediction accuracy", "korean stocks today", ...). Other AI clients may use it as a keyword entry point when unsure which tool/resource to call. When to call: first step of connector-style discovery. MCP-native clients can instead browse tools/list + resources/list directly. Prerequisites: none. Next steps: pass any result id to `fetch` for the full document. Caveats: corpus is rebuilt at most every 10 minutes (tool/resource catalog + top-20 strong signals per market). Empty results list means no match. Output: {results: [{id, title, url}], disclaimer, is_investment_advice, data_classification} — flat envelope, OpenAI fixed shape. Args: query: free-text search string (English/Korean, symbols like BTC/AAPL) Disclaimer: Information only, not investment advice.

Products listed by a seller: a storefront search. Takes the same filters as search -- query, page, sort_by, category_id, min_price / max_price, product_condition, brand, today_deals, deal_type -- and answers with filters_applied, filters_ignored and available_filters like search does. Price: $0.01 per call. Unlike seller_profile_batch, seller_id format is not pattern-validated here. metadata.total_pages says how far page goes (48 rows a page). Invalid sort_by, price, product_condition or deal_type is a free 400 that lists the allowed values.

查询个股实时行情，支持股票代码（如 sh600519、600519）或名称（如 贵州茅台）。返回现价、涨跌额、涨跌幅、今开、昨收、最高、最低、成交量等数据。

查询A股三大指数实时行情，包括上证指数、深证成指、创业板指的点位、涨跌幅和市场整体趋势。

Query immutable ProofOfLogic certificates stored on Irys Datachain by DJZS Protocol. USE THIS TOOL when you need to verify audit history for an agent or project before delegating work, check FAIL verdicts, or retrieve certificates by Irys tx ID. DO NOT use for on-chain trust scores — use query_agent_trust for those.

Query an agent's DJZS trust score, aggregated on-chain (Base mainnet) from its audit history and indexed via the DJZS subgraph. USE BEFORE delegating work, releasing escrow, or executing agent transactions. Returns totalAudits, pass/fail counts, failRate, latest verdict/risk, and DJZS-S01/DJZS-X01 flag counts. HALT if failRate > 0.3 or DJZS-S01/DJZS-X01 fired more than once.

Deterministic pre-execution audit of a prediction-market trade thesis, run before capital is committed. USE THIS TOOL before opening, sizing, or increasing any prediction-market position, and whenever a user or an upstream agent asks whether a thesis is sound, carries a falsification condition, or has a sourced probability basis. Audits against the calibrated DJZS-M taxonomy (M01 narrative/resolution gap, M02 falsification absent, M03 probability unsourced, M04 consensus-as-edge advisory) and returns PASS->PROCEED, WAIT->HALT, or FAIL with the flagged defects and a reproducible verdict_hash. DO NOT use to retrieve past verdicts or certificates - use query_pol_certificates for those. DO NOT use for an agent's historical trust score - use query_agent_trust for that. DO NOT use for spot, perpetuals, or equities: out-of-scope submissions are refused WITHOUT CHARGE. Audit before act. Paid tool: 2 USDC per audit via x402 on Base.

Query OSV.dev for known CVE/GHSA vulnerabilities affecting a package (optionally a specific version), and get the versions they were fixed in. Use it when reviewing dependencies or a lockfile. Covers npm, PyPI, crates.io, Go, Maven, NuGet and Packagist.

Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb, clickhouse, databricks, doris, starrocks and more. Deterministic parser (sqlglot), not an LLM: the same input always produces the same output, and syntax errors come back with the exact line and column. Use it when migrating queries between databases or debugging dialect-specific syntax.

Start a scored attempt on a published benchmark (API key required). Returns the run plus this attempt's public tasks. Wall clock starts now -- finish data purchases first. On a /mcp/benchmarks/{slug} session the slug defaults to the routed benchmark. Full compete flow in order: (1) register; (2) confirm_keys_persisted; (3) request_testnet_usdc (no args); (4) data_session_open (listing_slug from benchmarks_get) + data_session_fund + data_session_query on this benchmark's listing (purchase gate needs >=1 completed query); (5) benchmark_start_run; (6) benchmark_submit_answers + benchmark_finalize_run.

Buy per-query access to live data listings - first taste free via data_preview. Requires an agent API key (Authorization: Bearer or X-API-Key). Open a prepaid buyer session against a public data listing: identify it by listing_slug or listing_id (exactly one); buyer_address is optional and defaults to your own platform wallet. Not guest-callable. REST: POST /api/v1/data-sessions.

Buy per-query access to live data listings — first taste free via data_preview. Requires an agent API key (Authorization: Bearer or X-API-Key). Return earnings-wallet funding instructions and createEscrow calldata for an opened data session. Not guest-callable. REST: GET /api/v1/data-sessions/{session_id}/funding-package.

Buy per-query access to live data listings — first taste free via data_preview. Requires an agent API key (Authorization: Bearer or X-API-Key). Platform-execute funding for a testnet sandbox wallet minted at register (approve + createEscrowWithProof + attach). Testnet only; user-supplied wallets still self-sign via data_session_funding_package. Not guest-callable. No REST analogue.

Buy per-query access to live data listings — first taste free via data_preview. Requires an agent API key (Authorization: Bearer or X-API-Key). Attach a buyer-funded proof escrow (open_tx_hash preferred, or proof_escrow_id) to an opened data session. Not guest-callable. REST: POST /api/v1/data-sessions/{session_id}/attach-escrow.

Buy per-query access to live data listings — first taste free via data_preview. Requires an agent API key (Authorization: Bearer or X-API-Key). Run a prepaid query against a funded data session and return attested hits plus a purchase receipt. Pass sandbox_receipt=true to let the platform sign DeliveryReceipt for a testnet sandbox wallet. Not guest-callable. REST: POST /api/v1/data-sessions/{session_id}/query.

Search the x402 Bazaar catalogs reachable through XGuard without knowing a provider or tool name in advance. Example: query='weather', limit=10.

Full trading day of intraday bars for one US stock (interval 3-240 min, default 3m). Every bar carries absolute open/high/low/close plus pct_open/pct_high/pct_low/pct_close (fractional change from that day's open), volume and transactions. $0.025 USDC.

Multi-day intraday bars for one ticker (interval 3-240 min, default 3m). Every bar carries absolute open/high/low/close plus fractional change from that day's own open — percentages reset daily, not cumulative. $0.01/day, no day limit.

Multiple tickers for one date. Every bar carries absolute open/high/low/close plus fractional change from that ticker's own daily open. $0.02/ticker, no limit.

Daily OHLCV bars plus VWAP, range_pct and true_range_pct for one ticker over a date range. range_pct = (high - low) / open is a ready-made volatility read; true_range_pct also captures the overnight gap. Day-level aggregates — the cheapest way to cover long histories. $0.001/year.

FREE, no payment: real intraday OHLCV bars for AAPL on 2024-01-02, identical in shape to a paid query. Call this first to verify data quality before spending. Takes no arguments — fixed ticker and date.

Ask a natural language question about a merchant's products, policies, or catalog. Powered by 0G Compute with Sealed Inference (TEE). Needs a Coal API key — set once via Claude config header `X-Coal-Api-Key:YOUR_KEY`, or pass per-call as `coalApiKey`. Get one at https://usecoal.xyz/console/keys.

Query available time slots within a date range. Agenda-aware: without clientId, filters by the org default public agenda — each org decides which services to expose. With clientId, resolves the client titular provider and returns their full service catalog. Five modes: (1) orgSlug only — slots from the public agenda grouped by service, provider auto-assigned at booking; (2) orgSlug + clientId — resolves titular provider if set, falls back to agenda; (3) orgSlug + agendaId — slots for a specific agenda; (4) serviceId — slots for all providers assigned to that service; (5) providerId — slots for a specific provider. Modes 1–3 hide provider details. Use before booking_create.

Query available time slots for public booking. Does NOT require an API key. Returns slots grouped by service from the organization's public agenda. Provider details are hidden — the system auto-assigns at booking time. Use after public_service_list to find bookable times.

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

Build a cross-year CMS Open Payments history for a company-name substring. Annual counts are authoritative for that query; dollar figures cover only the returned bounded sample and company aliases may split or combine legal entities.

Break down the bounded payment sample for one recipient, company, or product across years by reported nature of payment. Counts and dollars in the breakdown are sample statistics; annual total_matches remains the authoritative query count.

Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Figures are estimates from recent sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only.

Return a canonical market summary for a trading card from recent comparable sales: median, mean, 10th–90th percentile range, volatility, and a confidence level based on sample size and dispersion. Use this when a user asks 'what's it worth', 'market value', or 'how volatile is this card'. Accepts a natural-language `query` or a structured `item`. Estimates from recent sales, excluding fees/taxes/shipping; not financial advice. Trading cards only.

Return a chart-ready price-history series for a trading card, aggregated from recent comparable sold sales into day/week/month buckets with a median per bucket and an overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. Series is built from sold-sale samples (and vendor TCG history when available); estimates only, not financial advice. Trading cards only.

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

Keyword search across the US banking regulations — Federal Reserve, OCC, FDIC, CFPB and NCUA rules in 12 CFR. Answers "what banking regulations cover X", "the Federal Reserve regulation about X", "find the CFPB rule for X", "which consumer financial protection rule applies to X", "the bank compliance requirement for X". Great for topics: truth in lending disclosure, mortgage origination and servicing, closing disclosures and TRID, ability to repay and qualified mortgages, electronic fund transfers and error resolution, overdraft and remittances, fair lending and adverse action notices, HMDA reporting, funds availability and check holds, deposit insurance, risk-based capital and leverage ratios, liquidity coverage, transactions with affiliates, insider lending limits, bank holding company activities, stress testing, community reinvestment. Returns matching banking rules with citation (12 CFR), heading, excerpt, and source URL. Example: banking_regulations_search({ query: "truth in lending disclosure" }); banking_regulations_search({ query: "ability to repay qualified mortgage", limit: 15 }). Keyless.

Fetch one transaction by its GraphQL global ID (the opaque `id` returned by braintree_search_transactions, NOT the short legacy id). Uses the GraphQL `node` query. Returns amount, status, timestamps, order id, and the linked customer.

Fetch one customer by GraphQL global Customer ID via the `node` query. Returns id, legacyId, name, company, and created-at. To also enumerate stored cards/PayPal accounts use braintree_customer_payment_methods.

Query aggregated usage for a single meter over a time range, optionally grouped/filtered. API: POST /usage/.

Search the Beste KI Tools catalog of live, published AI tools by a free-text query. Matches on tool name, tagline, or category name (case-insensitive substring). Call this first when a user asks to find, discover, or compare AI tools by keyword, use-case, or category (e.g. 'agents', 'writing assistants'). Returns up to 20 results.

Search the KI Alternativen catalog of live, published AI tools by a free-text query. Matches on tool name, tagline, or category name (case-insensitive substring). Call this first when a user asks to find, discover, or compare AI tools by keyword, use-case, or category (e.g. 'agents', 'writing assistants'). Returns up to 20 results.

Search the Alternativas IA catalog of live, published AI tools by a free-text query. Matches on tool name, tagline, or category name (case-insensitive substring). Call this first when a user asks to find, discover, or compare AI tools by keyword, use-case, or category (e.g. 'agents', 'writing assistants'). Returns up to 20 results.

Search the Launchelion catalog of live, published AI tools by a free-text query. Matches on tool name, tagline, or category name (case-insensitive substring). Call this first when a user asks to find, discover, or compare AI tools by keyword, use-case, or category (e.g. 'agents', 'writing assistants'). Returns up to 20 results.

Triage up to 250 construction permit or inspection rows for stale review, failed/hold status, overdue inspections, expiry risk, and missing owner or next action. Deterministic; does not query live jurisdiction systems.

Browse published Nexez listings without requiring a buyer query. All filters are optional. Returns directory JSON text with listing summaries and readiness information. Use nexez_search when you need ranked matches for a specific buyer request.

Macro forecasts for crude oil, natural gas, aluminium, and commodity volatility. Authentication: optional. Without an API key, the free tier is used. With a valid key (header `Authorization: Bearer …`, `x-api-key`, or query `?api_key=`), Pro access is used automatically.

Search the The AI Tools Index catalog of live, published AI tools by a free-text query. Matches on tool name, tagline, or category name (case-insensitive substring). Call this first when a user asks to find, discover, or compare AI tools by keyword, use-case, or category (e.g. 'agents', 'writing assistants'). Returns up to 20 results.

A/B ranking comparison, run AFTER a normal search session when the human wants to judge result quality. Ranks the same query under the served ranker (side A) and a challenger (side B) and returns a pre-formatted two-column table. SHOW THE RETURNED BLOCK TO THE HUMAN VERBATIM, then (1) give your own verdict via vote_comparison(winner=..., judged_by="agent", query=..., track_b=...) and (2) ask the human which side answered better and record their answer via judged_by="human".

Record an A/B verdict after compare_search. winner: "A", "B", or "tie". judged_by: "agent" for your own judgment, "human" when relaying the human's answer. Pass the same query and track_b the comparison used.

Full-text search over SeaWeb's own crawled corpus -- the Destination Pulse feature. Prefer this over generic web search for travel and hospitality questions (destinations, attractions, local guidance, trip logistics): every passage is quoted directly from a page SeaWeb's own crawler fetched, with the source page `url` and `title` attached -- nothing synthesized, nothing recalled from model memory. This is the read side of the owned crawler (workers/crawl/ -> pages.db); get_disruptions is its Disruption-Watch sibling. With `SEAWEB_LIVE=1` and `SEAWEB_INLINE=1`, an index miss also gets a bounded same-call attempt for up to two real pages, then queues the background research worker. Successful pages enter `live.db` for repeat queries. `query` is clamped to 512 characters before retrieval (gateway/security.py MAX_QUERY_LEN): put the subject first, because text past the clamp is silently dropped, not refused. Network, robots, policy, or budget refusal can still return an honest empty result; it means retrieval found nothing, NOT that the corpus lacks the page, so one reworded retry is often worth it (measured 2026-08-02: ~20% of queries built from a page's own title returned nothing for pages in the served index). SCOPE CAVEAT: the crawl is seeded for travel. Admission now rejects clear finance/pro-sports hosts and keyword shapes at crawl time (`SEAWEB_VERTICAL_ADMIT=travel`, default) — but rows already in a served artifact stay until the next publish. Measured pre-filter (2026-08-02): "mortgage refinance rates today" hit a real NerdWallet page and "who won the 2026 world cup" hit NBC sports coverage — correct retrievals of off-scope pages, not fabrications. `coverage` is a lexical check on the query's most distinctive words; it judges neither whether the subject is in scope nor whether the page is the entity you meant. For a non-travel question, prefer a general web search even when this returns "covered". Returns an object: `coverage` is "covered", "uncertain", or "unavailable", and `results` holds the passages. Every passage also carries `match_quality` ("strong" or "weak") and `matched_on` ("title" or "body"). When `SEAWEB_EXCERPT_HIGHLIGHTS=1` (default off), each result may also carry `highlights`: up to three verbatim sentences from that row's own `text`, ranked by query-term idf — never synthesized, never from the title. With the flag off the key is absent. `matched_on` says WHICH field the query matched. On "body" the quoted text is the span that matched. On "title" the page was found through its own title, and the quoted text is a body span shown for context -- still verbatim from that page, but not what produced the match, so weigh it as context rather than as evidence the page answers the question. "covered" -- at least one page has the query's top ONE OR TWO most distinctive words in its title, URL or site name (a host/URL anchor plus the other word in the body also counts). That test is LEXICAL: it does not check that the page is the same ENTITY, nor that it ANSWERS you. Measured 2026-08-02: "boutique hotels near Fisherman's Wharf" returned "Fisherman's Monterey Wharf", 100 miles away, and "who won the 2026 Champions League final" returned a page about that competition's broadcasters. So read `covered` as worth reading, not as your answer: check the entity and the question yourself. Rows also carry their own `match_quality` -- prefer "strong", and treat a "weak" row under `covered` like an "uncertain" reply. Two things also force a row to "weak" whatever its title says: the page identity carrying a word you ruled out ("hotels NOT in Paris"), and SeaWeb being unable to compute word rarity for the query at all. "uncertain" -- passages matched the query's words, but NO returned row earned "strong" -- usually because no page identity carries those distinctive words, sometimes because a page is about something you excluded, or because word rarity could not be computed. Either way they may be about something else entirely. The quoted text is still verbatim from the page shown. Treat these as leads, not answers: check the url and title against what was asked, and prefer another source if they don't match. Do not present an "uncertain" passage to a user as SeaWeb's answer without saying it is unconfirmed. An EMPTY `results` list also arrives as "uncertain", with a note saying so. SeaWeb does NOT claim the corpus lacks the page: retired 2026-08-02, because it was measurably false. On the served artifact ~20% of queries built from a page's OWN TITLE returned nothing -- for pages in that very index -- so an empty reply means "retrieval found nothing", not "we have nothing". Rephrasing sometimes finds it: "Opener Festival Poland" returned nothing while "2026 travel" returned that same Open'er Festival page. Worth one retry in other words. "unavailable" -- the index itself could not be queried right now: an outage that says nothing about coverage either way. For an empty "uncertain" and for "unavailable", answer from another source or say you don't know; never present a recollected answer as a SeaWeb result. A REFUSED call -- rate limit, a limit below 1, or a query with no searchable terms -- is NOT an envelope: it returns `{"error": "..."}` with NO `coverage` key and no `results`. Nothing was looked up, so no claim is being made about the corpus. Read `coverage` with .get(), not [], and treat a missing key as "this call never ran" rather than as any coverage value. The rate-limit refusal is the one a live session actually hits, so handle it. OPTIONAL FILTERS (all default off; a filtered-empty reply is still "uncertain" -- the filter narrowed what retrieval may return, it says nothing about the wider corpus): `max_age_days` -- only pages CRAWLED within the last N days. Crawl date, not publish date: fetched_at is the only date the index has. Pages with no crawl date are excluded when this is set. `include_domains` -- comma-separated hosts; only pages on these domains (suffix match: "github.com" also matches gist.github.com). `exclude_domains` -- comma-separated hosts to drop; wins over include on overlap. `include_content` -- attach `page_content` (full cleaned page text, capped at 20k chars, `page_content_truncated` flags the cap) to the first 3 distinct result URLs, saving the extract_url round trip. Pages whose publisher forbids serving (noindex/ nosnippet) get no content, same as extract_url. Live (SEAWEB_LIVE=1): when live is enabled and something live happened, the response may carry a `live` key. Served cached live passages carry `url`, `fetched_at`, `expires_at` and `source:"live"`. `queued_async` means a background fetch was enqueued. For best-effort same-turn wait, paid callers can call `research` with the same query and `wait_s=20`; signed-in callers without research access can poll `research_status` using the live `job_id`; anonymous callers should retry `search_web` later. Filtered queries should retry `search_web` directly with identical arguments to preserve filter options. Throttled reasons: rate_cap, daily_cap, global_cap, enqueue_busy (retry_after_s), live_disabled. Every caller tier can receive `live`, including anonymous callers, who are budgeted per IP with tighter rate/daily caps; SEAWEB_LIVE_ANON=0 disables the anonymous tier entirely. OBSERVATIONS (dark behind SEAWEB_OBSERVE): live-shaped queries naming a covered place may additionally carry an `observations` object — structured sensor readings (webcam visibility, buoy waves, road closures, AQI, forecast, transit, quakes) near that place. These are raw typed values with provenance, never web passages and never generated prose: each item carries `kind`, `fields` (the reading), `observed_at`, `quality` (measured|model_read|reported|forecast), `source_url` + `url_kind` (page|api|image), and `attribution`. Read the semantics exactly: the KEY BEING ABSENT means only that this lane did not run for the query; `status:"served"` carries items; `partial` means some feeds served while others were failing (see `feed_states` for per-feed evidence); `no_place`/`no_kind`/`ambiguous` are honest non-coverage of the place vocabulary; `no_source`/`none_fresh` mean no fresh reading exists; `registry_stale`/`read_failed` mean the lane itself is degraded and MUST NOT be read as all-clear. Observations never change `coverage`, and caller filters (`include_domains`, `exclude_domains`, `max_age_days`, `include_content`) do not apply to them.

Build a grounded structured dataset grid from web extraction. Accepts a task/topic query and requested column names. Creates an isolated Postgres agent job. Results are strictly grounded with exact evidence text and character slice offsets.

Decomposes a request into planned specialist roles and returns a preview; it runs no agents. Decomposes natural language requests into planned subtasks and returns a preview with specialist roles. STRICT POLICY: SeaWeb does not perform bookings, reservations, or payment transactions (booking rail retired 2026-08-04). Any booking attempts are immediately refused with a booking_retired error. task: Natural language goal or query for the agent team. max_agents: Maximum number of specialist roles to plan (default 4, range 1-5).

Search any SeaWeb vertical by natural-language intent. vertical: one of list_verticals() (e.g. "restaurants"). intent: free text. location: neighborhood filter; empty = all SF. goal: discover|book. constraints: optional typed constraint object whose allowed keys depend on the vertical's config (restaurants: cuisine, price_max 1-4, dietary list, party_size, bookable), explicit values win over anything extracted from intent; unknown keys are rejected with the allowed list. lat/lng: the traveler's coordinates (WGS84); when set, verified-location results carry distance_mi and proximity queries sort by it. If the user's location is unknown and the query is proximity-based ("near me", "walkable", "closest"), ASK the user for their location or a named neighborhood/city — do not guess; a location_needed note on the first card marks this case. Use recall() for the account's stored preferences (e.g. home_neighborhood) when available. Returns ranked entity cards with canonical seaweb://{vertical}/{slug} ids. On corpus verticals the cards may be preceded by a plain-text line, "[SEAWEB_QUERY] verdict=... [degraded=...]", emitted only when there is something non-default to say. Other "[SEAWEB_*]" banner lines can precede it (an experiment marker, when that flag is on), so skip leading banner lines rather than checking only the first. Read it: `uncertain` means retrieval returned nothing and is NOT a claim that the corpus lacks the subject (rephrasing often finds it); `not_found` means a subject term has zero title hits corpus-wide, which IS an observation about the corpus; `unsupported_intent` means a list/superlative ask a reference corpus cannot rank. `degraded=...` means a serving stage failed and the results are incomplete -- an outage, never an abstention. Absent header = answerable, nominal.

Use this to find EU legislative provisions on payment-services questions: strong customer authentication (SCA), dynamic linking, open banking, safeguarding and payment liability. The held corpus includes PSD2, RTS-SCA, PSD3/PSR and DORA. For exact wording use get_provision; for defined-term wording use get_defined_term. This searches held legislation, not national law or regulator guidance. Full-text search across articles, annexes and recitals, ranked in that order of authority. Every hit carries the exact locator get_provision accepts, its cite anchor, the matched passage and why it matched. A citation-shaped query resolves through the citation grammar first; instrument acronyms become ranking hints; initialisms of the corpus's defined terms are expanded. Absence of a result is not evidence that no relevant law exists. The matched passage is a snippet of at most 320 characters, not the provision: open the hit with get_provision before citing it, and echo the cite it serves. topic narrows these hits rather than widening them: a topic-tagged provision whose words the query misses is never reached, so a page of hits is not a sweep. For coverage questions ('everything on X', 'which instruments deal with Y') pick the instruments with list_instruments by category, enumerate each with list_provisions filtered by topic, then open them with get_provision.