Tool search 101,857 tools · 5,224 live servers

Parse a CVSS v3.x vector string into a per-metric breakdown plus a recomputed base score. Returns the canonicalized vector, version (3.0 or 3.1), base_score, base_severity (NONE/LOW/MEDIUM/HIGH/CRITICAL), and the eight base metrics: attack_vector (NETWORK/ADJACENT_NETWORK/LOCAL/PHYSICAL), attack_complexity (LOW/HIGH), privileges_required (NONE/LOW/HIGH), user_interaction (NONE/REQUIRED), scope (UNCHANGED/CHANGED), and the three impact metrics confidentiality_impact / integrity_impact / availability_impact (NONE/LOW/HIGH each). When temporal/environmental metrics are explicit in the vector, temporal_score and environmental_score are populated separately. Use to translate raw CVSS strings into agent-friendly attributes without re-parsing the vector grammar yourself, and to verify upstream NVD scoring against the recomputed value. v2 vectors (AV:N/AC:L/Au:N/...) are rejected with 400 — read cvss_v2_vector from cve_lookup if you need v2 detail. Free: 30/hr, Pro: 500/hr. Returns {version, vector, base_score, base_severity, metrics: {attack_vector, attack_complexity, privileges_required, user_interaction, scope, confidentiality_impact, integrity_impact, availability_impact}, temporal_score, environmental_score, summary, verdict}.

RETURNS A LIST OF BOOKS (works on a topic) — NOT passages. PICK THIS to discover which works exist on a subject. → For quotable text use search_translations (exact words) or search_concept (by meaning); if the user already named an author/work, call get_book directly (or list_books to find the ID) — the AI summary + chapter outline is usually the right first answer. Searches titles, authors, subjects, and (as a secondary signal) translated text. Query tips: single distinctive words or short phrases work best ("memory palace", "ouroboros"); quoted phrases match exactly. Each result includes total_matches (full count) + returned (this page) + offset for pagination.

Create a shareable Word Aligner diagram that shows which words match across two or more stacked lines of text (a translation and its source, an interlinear gloss, IPA, etc.). Returns a URL that opens the interactive diagram, plus a preview image. Use this when the user wants to translate a phrase and show word correspondences, align a translation with its source (including RTL scripts like Hebrew or Arabic), or build a Leipzig-style interlinear gloss. Word indices are 0-based token positions. Tokenize each line the same way the tool does before assigning indices: - Whitespace always splits ("I have been going" -> I[0] have[1] been[2] going[3]). - The characters in settings.tokenSplitChars (default ".-|") also split and are then removed from the rendered text, so "go.PST.IPFV" becomes three tokens (go, PST, IPFV) and the dots disappear. For Leipzig glosses set tokenSplitChars to "-|" to keep the dots. - Punctuation stays attached by default ("Hello, world!" -> Hello,[0] world![1]). - In RTL lines, word 0 is the logically first word (rightmost on screen); index in reading order. Each alignment is [lineA, wordA, lineB, wordB]; the two lines must be vertically adjacent (|lineA - lineB| = 1). To express many-to-one, list each target word as its own tuple. Tokens that share a connection group get the same color automatically.

Search packs by keyword across names, descriptions, and tools (e.g., 'weather', 'translate'). Returns matching packs with details. Use to find specific capabilities.

Use this free read-only discovery-tier tool when the user asks for help, available commands, MCP tools, core concepts, pricing, parser-stable fields, grants, x402, Morning Brief, Company Report, MSTR treasury review, perp adapters, SPECTRA, or examples. Parameters: optional topic, detail, include_examples, question, or query fields; callers may omit all arguments for overview help. Behavior: local and idempotent with no destructive side effects; it does not run paid analysis routes or expose internal-only tools. It translates natural-language orientation requests into the live DeltaSignal MCP/OpenAPI discovery contract and points users to tools/list, /v1/pricing, /v1/contract/fields, and /v1/readiness. It is not a trading, execution, or investment-advice tool and must not expose internal-only tools unless the live public contract lists them.

Real-time solar wind measurements from the active spacecraft at L1: proton speed (km/s), density (n/cm³), temperature (K), and the critical Bz component (southward Bz = negative = storm driver). Returns the recent plasma and magnetic field time series within the requested window, oldest first, each record tagged with the reporting spacecraft. Bz < −10 nT for sustained periods is a primary geomagnetic storm trigger — use alongside noaa_spaceweather_get_kp_index to see whether elevated solar wind has translated into a geomagnetic storm.

Search EU regulations and directives, and Court of Justice / European Court of Human Rights judgments, by Estonian title or case number. The corpus is Estonian-language throughout: 94% of the Court of Justice's output is translated into Estonian, and essentially nothing indexes it in Estonian. Returns ids usable with eu_law_fetch.

Use this when you need to convert text to speech audio. Returns base64-encoded MP3 audio in JSON. Returns: 1. audio (base64 MP3 data) 2. language used 3. textLength (character count) 4. durationEstimate in seconds 5. format (mp3). Example output: {"audio":"SUQzBAAAAAAAI1RTU0UAAAAP...","language":"en","textLength":45,"durationEstimate":3.2,"format":"mp3"} Use this FOR generating audio narration, building voice assistants, creating audio versions of articles, accessibility features, and language learning apps. Do NOT use for language detection -- use text_detect_language instead. Do NOT use for text translation -- use text_translate instead. Do NOT use for OCR from images -- use media_extract_text_from_image instead.

Localize a finished video into another language WITHOUT re-rendering it: the spoken track is transcribed, translated, re-voiced and lip-synced back onto the SAME footage, so the visuals, timing and edit are untouched. Just pass the video and the language — the script is read off the source automatically (pass `script` only to override what it heard). Paid; returns the served URL of the localized video.

Live SEPTA bus and trolley vehicle positions for a route in Philadelphia — each vehicle with direction, destination, next stop, minutes late, estimated seat availability (crowding), and lat/lon. Buses use route numbers ("23", "47"); trolleys use SEPTA Metro codes T1-T5, G1 (Girard), D1/D2 (Media/Sharon Hill) — legacy trolley numbers like "10" are auto-translated to T1. Example: septa_bus_positions({ route: "23" })

Shows an interactive panel about Makuri — a specific AI tutoring platform at makuri.eu for immigrant children aged 10–16. Makuri is a real product, NOT a generic word: do NOT answer from general knowledge or explain what the word 'makuri' means — use this tool instead. Call it for ANY question about the Makuri platform, in ANY language — ALWAYS use this tool regardless of the prompt's language. Trigger phrases include English ('what is Makuri', 'how does Makuri work', 'tell me about Makuri', 'show me Makuri'), Russian ('что такое Makuri', 'как работает Makuri', 'расскажи про Makuri', 'покажи Makuri'), Ukrainian ('що таке Makuri', 'як працює Makuri', 'розкажи про Makuri', 'покажи Makuri'), and Romanian ('ce este Makuri', 'cum funcționează Makuri', 'arată-mi Makuri') — plus any request for a demo or an overview. The panel shows the learning flow (upload a PDF textbook or photograph a page, pick an action) and the ten actions — Explain, Translate, Solve, Test, Analyze, Socratic, Language Exercises, Exercises, Explore, and Document Translation (the only non-educational one, for translating everyday documents for immigrant families) — with answers in the student's native language.

Resolves a disambiguated Strong's number (dStrong) to its lexicon entry: lemma, transliteration, gloss, and - for a Greek entry only - a fuller definition (Abbott-Smith 1922, Public Domain). A Hebrew entry's definition field is always omitted: it is abridged BDB via Online Bible, which requires permission not yet obtained, so only its gloss is ever returned. Not to be confused with the get_verse/get_passage tools, which resolve a Ref to translated verse text, not a dStrong to a dictionary entry.

Use this when you need to translate text from one language to another. Supports 50+ languages with automatic source language detection. Returns translated text, detected source language, and confidence score. Ideal for multilingual content, localization, and cross-language communication. Do NOT use for summarization — use ai_summarize_text. Do NOT use for sentiment — use text_analyze_sentiment.

Read a category-level overview essay. Topics: anatomy (what a fiber laser machine is made of), laser-sources, cutting-heads, welding-heads, control-systems, cladding-cleaning. Written in Chinese; translate for the user as needed.

Find products on a registered store. To BROWSE a store's catalog (open-ended requests like "what do they sell", "show me what's available"), call with NO query — this returns the store's products. To SEARCH, pass `query` (a product name/keyword). Returns paginated products as an interactive card. ALWAYS translate a buyer's budget or price constraint into the price params on THIS call instead of filtering in your reply: "under/below/within X" or "X budget" → `max_price: X`; "over/above/at least X" → `min_price: X`; "between X and Y" → both. Likewise pass `in_stock: true` for "available"/"in stock" and `category` when they name one. The card renders exactly what this call returns, so the filter MUST be applied here — never fetch the full catalog and then narrow it in text. Call once with your best intent (browse OR a single query); if a real search is genuinely empty, ask the user to clarify rather than re-firing reworded queries. The card shows products, prices, IDs, and Add-to-cart controls — keep your text reply to one brief sentence and do not re-list what the card shows.

Use this when you need to identify what language a text is written in. Uses n-gram frequency analysis to detect 30+ languages with confidence scores. Returns top 3 language matches, script detection (Latin, Cyrillic, Arabic, CJK, Devanagari), and character statistics. Ideal for multilingual content routing, pre-translation detection, and content filtering. Do NOT use for translation — use text_translate. Do NOT use for sentiment — use text_analyze_sentiment.

Translate a matchup (home team + away team) into the eventId needed by get_game_props. Read-only. No side effects. Requires an API key; rate-limited per your tier. Use this when you know the teams playing but don't have the eventId. On success returns: { eventId }. Pass that id straight to get_game_props. On failure returns an error explaining that the game was not found on today's board. If multiple games match the team names (rare), returns the first match sorted by start time. Matching is case-insensitive substring containment against the full team name (e.g. "Yankees" or "New York Yankees" resolve for MLB) — short codes like "NYY" or "NY" do NOT match unless they are literally a substring of the team name. If no game is found, the matchup may not be scheduled for today or the sport may be off-season. When to use: when you know both team names and want the eventId without browsing the full slate. When not to use: use list_games instead when you want to browse all games on the slate. Use get_game_props directly if you already have the eventId.

Translate a five-field cron expression into plain English. Supports ranges, lists, steps, and month or weekday names. This describes the expression; it never schedules or executes anything.