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

Answers "which stocks scored highest on measured DART financials?" — kind='growth' is 성장 TOP8 (max 8 rows), kind='quiet' is 조용한 실적주. Scores come from a published formula over ACTUAL filed financials only — no prices, no analyst estimates. Mechanical, not stock picks. For 52-week high/low or turnaround LISTS use list_stocks(). | "실측 재무로 점수가 높은 종목"에 답합니다 — growth 는 최대 8건, quiet 는 조용한 실적주. 시세·전망치를 쓰지 않고 DART 실측 재무만 씁니다. 52주 신고저·흑자전환 목록은 list_stocks().

Direct URLs for every public dataset (JSON/CSV) — no signup, no API key. Call this BEFORE concluding something is unavailable: the tool list is not the extent of the data. Returns the endpoint catalog (quotes, disclosures, rankings, per-stock JSON, search index) plus the 30-trading-day dated archive with the exact dates held per pattern. Most AI fetch tools cut responses near 150 KB and a truncated JSON is unparseable — the catalog names a smaller alternative for every large file, so read that instead of guessing. | 전체 공개 데이터(JSON·CSV) 직링크 카탈로그 — 무가입·무키. **없다고 결론내기 전에 먼저 부르세요**: 도구 목록이 데이터의 전부가 아닙니다. 최근 30영업일 날짜별 아카이브(패턴별 보유 날짜 포함)도 함께 냅니다. 대부분의 AI 가 응답을 150KB 안팎에서 자르고 잘린 JSON 은 파싱되지 않습니다 — 큰 파일마다 소형 대체본이 카탈로그에 적혀 있으니 그쪽을 쓰세요.

Quarterly earnings from DART, INCLUDING preliminary (잠정) results filed ~2 weeks before the regular report. Pass a code for one stock's history, or omit it for the largest caps. get_stock returns the REGULAR report only — use this for the newest numbers. | DART 분기 실적 — 정기보고서보다 2주 빠른 잠정실적 포함. code 를 주면 그 종목 이력, 생략하면 시총 상위. get_stock 은 정기보고서만 주므로 최신 수치는 이 도구로 보세요.

Answers "who has filed this quarter's results, who hasn't, and what came in since last time?" — filed / not-yet lists against the statutory deadline, plus a diff of filings new since the previous publish. Built for stateless agents: polling this replaces a webhook. | "누가 냈고 누가 아직인가 · 지난번 이후 새로 뜬 건 뭔가"에 답합니다. 법정 마감 D-day 와 직전 발행 대비 신규 목록까지. 상태를 못 들고 다니는 에이전트를 위한 도구입니다.

Answers "what was filed, and when exactly?" — DART filings with RECEIPT TIME (HH:MM) and session (pre-open / intraday / after-close), filterable by date, type and importance. The receipt time is not exposed by any public Korean API. Roughly 40% of filings arrive AFTER the close, so that day's price move is not a reaction to them. date=today serves the 15:00 intraday collection (no importance scores yet); any other date serves the ranked list of the last 7 days. | "무슨 공시가 몇 시에 났나"에 답합니다 — 접수 시각(HH:MM)과 장 구분까지. 공개 API 어디에도 없는 값입니다. 날짜·유형·중요도로 거를 수 있습니다. 접수분의 **40% 안팎이 장 마감 후**라 그날 등락은 그 공시의 반응이 아닙니다. date=오늘이면 15:00 장중 수집본(아직 중요도 점수 없음), 다른 날짜면 최근 7일 상위 목록입니다.

Return the identity behind the configured API key: userId, keyId, granted scopes, plus the key's agentName and agentModel (both null until set in Profile -> API Keys; agentModel is the self-reported model/runtime label shown on the public Agent Arena when opted in). Use this first to confirm what the key is allowed to do. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

One agent's public Arena profile by handle (the `handle` field from get_arena_leaderboard, e.g. 'a42-momentum-scout'): rank, total + per-venue realized PnL, decided/total trade counts, and win rate. Public data only — no account or key identity. Paper trading only — virtual funds (50,000 mUSD). Not financial advice. Paper fills run under the versioned paper_execution_v1 policy and apply a disclosed execution cost folded into realized PnL: spot/futures pay a taker fee (spot market orders also pay half-spread + slippage); PM fills at the ask with size-based slippage and a Polymarket-shaped taker fee, with entryProbability kept at the mid for calibration. See the executionModel in quote/trade results — a rehearsal cost, not an exchange fill guarantee.

Builds a Merkle-rooted disclosure manifest from a caller-supplied digest list (DATAROOM-1-BUILD-SPEC.md §DR-4) -- the agent hashes files itself and passes {path,size,digest,content_type} entries; the worker never sees file contents. Same leaf scheme as tools/546-disclosure-manifest-builder.html: sha256(path|digest|size), duplicate-last-leaf on an odd level. Entries are sorted by path before hashing so the root is order-independent. Returns the manifest object + merkle_root; sign and anchor it client-side (or via a separate §16 signing step) if a signed artifact is required.

Proves (or refutes) that a {path,digest} pair was in a disclosure manifest's room (DATAROOM-1-BUILD-SPEC.md §DR-4) -- worker-side mirror of tools/547-disclosure-manifest-verifier.html's single-file inclusion check. Recomputes the manifest's Merkle root over its entries[], builds the inclusion proof path for the target entry, and reapplies it to confirm it reduces to the claimed merkle_root. Absence is only provable against the exact manifest version passed in.

Render a verified OpenChainGraph v0.4 artifact into a chaingraph_export profile (OCG Standard §13). Generated downstream of and EXCLUDED from the execution_hash preimage — the export is a view, not a fact; verification always routes back to the canonical JSON artifact. Pass the FULL artifact you received from a compute tool (the server is stateless — there is no hash cache). Formats: xlsx, csv, pdf, xbrl (xbrl_taxonomy="ocg-ext" works now; eba-corep-* return a pending error until their concept maps are populated from the published EBA taxonomy), and vc — a W3C Verifiable Credentials 2.0 rendering (OCG §13.11, application/vc+json) available on every node; it re-states the canonical execution_hash via ocg:hashAnchor and mints no new hash/proof. readOnlyHint: true; zero PII, zero payload logging.

Validates a checklist or SOP definition JSON against the CHECKRUN-1 schema (definition_id, title, semver version, non-empty steps[] each with step_id/title/instruction/evidence_requirement (none|text|file-digest|attestation)/gate (blocking|advisory)). Returns valid:true/false plus a field-by-field error list. Pair with checklist_step_receipt to run the definition headlessly.

Canton Tokenization Readiness Diagnostic: OpenChainGraph compute node (readiness_diagnostic). Deterministic OpenChainGraph compute node. By default (compute:"auto") inputs are computed server-side on Cloudflare Workers for gpu:false nodes with a registered kernel; compute:"browser" forces client-side execution and returns a browser delegation URL instead. gpu:true nodes always delegate to the browser. Inputs are processed transiently to compute the response and are not stored, logged, or retained. Use synthetic or anonymised inputs only. Exports an AP2 artifact with execution_hash for chain provenance. Output feeds: 504-settlement-risk-capital-optimizer. Open at: https://ainumbers.co/tools/503-canton-tokenization-readiness-diagnostic.html FV-status (published/proven/still-trusted for this spec): /fv-status/c8732274c0bffae6490feffd076030312786535484e4ebb4e779ce7a89e0725c.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched.

Settlement-Risk Capital Efficiency Optimizer: OpenChainGraph compute node (capital_assessment). Deterministic OpenChainGraph compute node. By default (compute:"auto") inputs are computed server-side on Cloudflare Workers for gpu:false nodes with a registered kernel; compute:"browser" forces client-side execution and returns a browser delegation URL instead. gpu:true nodes always delegate to the browser. Inputs are processed transiently to compute the response and are not stored, logged, or retained. Use synthetic or anonymised inputs only. Exports an AP2 artifact with execution_hash for chain provenance. Consumes upstream artifacts from: 503-canton-tokenization-readiness-diagnostic. Open at: https://ainumbers.co/tools/504-settlement-risk-capital-optimizer.html FV-status (published/proven/still-trusted for this spec): /fv-status/c8732274c0bffae6490feffd076030312786535484e4ebb4e779ce7a89e0725c.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched.

Get current operator profile and status

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Profile of a legal entity (company or public body) by 9-digit ΑΦΜ: name, role, and spend/receipt statistics as buyer and as supplier. EUR totals = the COMMITTED procurement value counted ONCE per procurement (deduplicated across ΚΗΜΔΗΣ/Διαύγεια sources and the award→contract→payment lifecycle; tenders/budgets excluded), so it reflects real committed spend, not a sum of every published act.

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Purpose: Multi-layer explanation for a single symbol's recent research signal. Combines (1) technical score_trace from the signals store, (2) Thompson + regime scores from the virtual decision log (Thompson = Bayesian bandit sampling used for strategy selection), (3) news causality context. Use this when an AI must present a structured "why" rather than a raw verdict. Triggers (casual questions too): "why is BTC bullish?", "왜 이 종목이 매수야?", "explain that signal", "판단 근거 설명해줘", "walk me through the reasoning". When to call: when the user asks "why is this signal bullish/bearish?". Prerequisites: identify the symbol via get_signals or get_latest_decisions first. Next steps: none (this completes the explanation chain). Caveats: `symbol` must match the per-symbol signal store filename (lowercase). Output is research evidence, NOT a buy or sell recommendation. Args: market_id: Market identifier (crypto, kr_stock, us_stock; aliases coin/kr/us) symbol: Symbol to explain (e.g., btc, eth, 005930) Disclaimer: Information only, not investment advice.

Returns the storefront profile for each seller id: business name, rating, feedback counts, address and marketplace presence. Price: $0.012 per item (max 10). Seller ID validation is all-or-nothing: one malformed id rejects the entire request with 400.

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.

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Look up ETFs by name, ticker or ISIN, with classification, listing, index, distribution-policy, AUM, expense-ratio and yield filters. Best for finding a known fund. For ranking questions ("cheapest", "largest", "best performing", "most liquid") prefer screen_etfs, which evaluates the whole universe: here minAum and minYieldTtmPct are applied only to a bounded profile-enriched candidate scan, so do not describe the result as exhaustive when candidateCapReached is true. Use get_etf_snapshot for one listing, get_etf_fund to resolve an ISIN across venues, and get_etf_holdings for constituents. Read-only.

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.

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Find the TrustyCap capability that solves a specific problem: add secure file storage, add application data, run work in the background, schedule work, make webhooks reliable, secure credentials, send transactional email, read documents, move money on proof. Returns every public capability: what it is for, when to choose it, what it will not do, the scopes a key needs, the meters it charges and the published price of each. Call this before assuming a capability exists. Covers vehicle intelligence, financing intelligence, document intelligence, protected transactions, digital life, exit paths and financing math.

Everything needed to install one Native Kit without reverse-engineering the application it came from: every file it ships with its content hash and the production path it was cut from, every pinned dependency and why that pin, every permission, entitlement, background mode and plist or manifest key with what breaks when it is absent, the JavaScript interface, the configuration that must not be changed and the reason for each, the ordered install steps including the ones that need a human in Xcode or a provider console, what is proven and how, and the real constraints. Read this before touching a native project.