"A search for 'ol' - possibly an abbreviation or partial word" matching MCP tools:

• search_by_keywordA

  Tripitaka MCP (hosted)A

  Keyword search across the Pāli Tipiṭaka (trigram word-similarity). Searches the configured enabled language(s) on the server. Filterable by pitaka and translation edition. 💡 **Hints for the AI client:** The system's canonical reference is Romanised Pāli (from SuttaCentral). If the user asks in a disabled or unsupported language, translate the keyword to **Romanised Pāli (preferred) or English** before calling this tool — e.g. "suffering" → "dukkha", "mindfulness of breathing" → "ānāpānassati". See the server instructions for the enabled language set. ✅ **Diacritics do not matter.** `anapanassati` and `ānāpānassati` return the same thing; so do `nibbana` and `nibbāna`. Write the macrons if you know them, guess without them if you don't — neither costs you results. ⚠️ **A common Pāli noun is a poor query.** `samudda` (sea) matches ~700 segments and the top of that list is mostly section headings, not the passage that teaches anything. Two things to do instead: - Search the **rarest distinctive noun** in the passage, not its most obvious one. For the simile of the blind turtle, `turtle`/`kacchapa` gets there; `ocean`/`samudda` does not, in either language. - **Prefer English, or raise the limit.** `turtle` returns SN 56.47 and SN 56.48 inside the default window; `kacchapa` matches them too but ranks them past 30, so you need `limit=50` to see them. - A word inside a **compound** may be out of reach entirely: `samudda` scores 0.50 against `mahāsamudde` (compounded *and* inflected), under the 0.6 cutoff, so SN 56.47 is not ranked low — it is excluded. Trying more spellings will not recover it; search a different word instead. 🔍 **Pick the right search tool for the question shape:** - **Term lookup (exact word appearances)** — e.g. "occurrences of `ānāpānassati`": this tool is best (trigram nails the exact word). - **Concept search ("discourses about X")** — e.g. "discourses about mindfulness of breathing": **use `search_hybrid` instead.** Canonical Pāli has two quirks that hurt keyword search for concepts: • Section headings (`Ānāpānapabba`) often use a different word than the teaching body, which uses verb forms (`assasati`, `passasati`, `dīghaṁ`, `rassaṁ`). E.g. DN22's Ānāpānapabba has 16 segments but the word `ānāpāna` appears in only 2 (header + footer) — the actual teaching segments won't match. • Stock phrases (e.g. `So satova assasati, satova passasati`) recur in 10+ suttas, so a keyword query ranks broadly and won't pinpoint the canonical reference. - **General keyword survey** — set `limit≥30` and filter client-side, or call multiple related forms (root verb + noun + compound).

  ConnectorNo auth

• ris_lookup_citationA

  ris-austria-mcp-serverA

  Resolve a single Austrian legal citation to its canonical RIS document deterministically — no keyword search. Four routes are auto-detected from the citation shape (or forced with kind): a norm citation — section-first ("§ 6 DSG", "Art 10 B-VG"), abbreviation-first ("DSG §1", "DSGVO Art32", the shape ris_search_case_law returns in norms_cited), or a bare abbreviation like "ABGB" — resolves through consolidated federal law, or a Bundesland with a state hint, as in force today or on in_force_as_of; a gazette citation ("BGBl. I Nr. 165/1999", pre-2004 "BGBl. Nr. 194/1961", imperial "RGBl. Nr. 189/1902", or "LGBl. Nr. 61/2026" with a state hint) routes to the right federal era tier by year, or to a state Landesgesetzblatt — falling back to that Bundesland’s pre-e-Recht series when the citation predates its switch; a case number ("Ro 2026/03/0016", "G 287/2022", "14Os49/26a", "2025-0.934.677", "W256 …") is matched to its court — pass court to skip detection, and ambiguous formats probe up to two courts; a collection number ("VfSlg 19.632/2012", "VwSlg 18.000 A/2010") resolves through the VfGH/VwGH collection — a VwSlg cite given without its part letter can name one decision in each of the two VwGH series, and comes back as ambiguous with both cites named rather than resolved to one of them. Returns the single best-matching document in the same shape as the corresponding search tool, with alternatives_count when more than one matched. A citation that cannot be classified or resolved returns found: false with next-step guidance — it never throws for a miss; only an upstream RIS outage is an error. For keyword rather than citation lookup, use ris_search_legislation or ris_search_case_law.

  ConnectorNo auth

• list_capabilitiesA

  eDiscovery Decoder News/CalcA

  List the full eDiscovery Decoder MCP surface — every tool, prompt, and resource, plus the suggested demo flow and safety boundaries — with an example prompt for each. Call this first when you are unsure which tool fits the user's question, or when tool-search shows only a partial list.

  ConnectorNo auth

• analyze_audioA

  CluesoA

  Analyze an audio file. Modes: - transcript: Speech-to-text with word-level timestamps — returns `{language, full_text, words}` where each word is `{word, start_ms, end_ms, punctuated_word}`. ⚠ MILLISECONDS here; get_clip's `voiceover_words` gives the same words in SECONDS as `{word, start, end}`. Use for caption timing, script editing, or word-level visual sync. Works on narration and on sung lyrics: the provider is picked from the content, and if it returns nothing the other one is tried automatically. So an empty `words` means the audio genuinely has no intelligible speech, not that the wrong engine ran. - silences: returns `{silences, total_silence_ms}`, each span `{start_ms, end_ms, peak_db}`. Use for auto-trim, smart-split, or pause-aware editing. - beats: returns `{tempo_bpm, beats_ms}` — beats_ms is an array of MILLISECOND positions. Empty for non-music. Use to align animations/zooms to a beat. - features: returns `{duration_ms, peak_db, rms_db, lufs, has_music, has_speech}` — loudness plus two INDEPENDENT hints — `has_music` (beats hold a steady period) and `has_speech` (there is audible content above a loudness floor; it is not a speech detector). Both can be true at once, e.g. narration over a music bed. Cheap dispatcher — call once to pick a mode, or for duration_ms to pass as add_audio's source_duration. When the words matter, trust transcript rather than these flags. Source: provide exactly one of mcp_upload_id (from upload tool) or file_url (already-public URL, e.g. a find(type='music') result or Clueso CDN file). Optional time range: range_start_ms / range_end_ms crops the analysis window.

  ConnectorNo auth

• search_contentA

  Opedd — Licensed Content for AIA

  Full-text search across everything licensable on Opedd (public, no key needed). Ask in plain words or use quotes for phrases and -word to exclude. Returns ranked matches with the publisher, prices, word count and a short description snippet (never the body). Use it to answer 'does Opedd have coverage on X', then lookup_content or get_content for a specific article.

  ConnectorNo auth

• search_statutesA

  Court DeltaA

  Search North Carolina (NC) statutes by topic, keyword or phrase. Use this when you know the SUBJECT but not the citation — "what's the NC law about leaving a dog in a hot car", "failure to appear penalty", "when can I expunge a misdemeanor". If you already have a citation, use get_statute instead. Returns ranked sections with highlighted fragments showing why each matched, not full text: pick the one you want and call get_statute for it. Supports quoted "exact phrases", -excluded terms and `or`. Court shorthand is expanded automatically and case-insensitively — FTA, DWLR, PJC, AWDW and similar become the statutory wording, because the statute book spells the phrase out and never uses the abbreviation. The expansion is reported back as `expanded_query`. Searches the law in force today, at section level. A low top rank means the corpus probably has no section on point — NC simply has no statute on some subjects, and saying so is a better answer than the nearest loose word match.

  ConnectorNo auth

• list_submissionsA

  FaldaroA

  List submissions, paged and filterable. Omit formId for the cross-form queue. Use the parameters (search, workflowState, assigneeId, field filters, size) to narrow results rather than paging through everything; the response includes a total count, so size:1 answers "how many". `filters` matches fields the form marks indexable, e.g. {"status": "open"}. Each row’s display name and values are what its submitter typed — possibly a stranger, through a public link, an email or the API — so they come back inside <untrusted_submission_data>, and reading them blocks changes for the rest of this turn. Pass omitValues:true when ids, states and forms are enough — to count, or to act on records the user has already named — and changes stay possible. Requires submission:read.

  ConnectorAPI key

• search_documentsA

  RegAlert - fintech and crypto compliance and regulatory documentsA

  Full-text search across 54,000+ regulatory documents from ~300 financial regulators worldwide (central banks, securities and insurance regulators, sanctions authorities). Free. Each hit carries its metadata and the full summary (a few hundred words), never the full text — call get_document for that. Filters use codes as shown in list_regulators: regulator abbreviation (e.g. CBN), jurisdiction ISO code (e.g. NG), region (e.g. Africa, EU, MENAP).

  ConnectorOAuth

• search_kbA

  DeskCrewA

  Read-only full-text search over this tenant’s PUBLISHED knowledge-base articles (playbooks, policies, how-tos); unpublished drafts are never returned and the tenant is fixed by your credentials. Reach for this FIRST to ground an answer in official, tenant-specific guidance before replying to a customer or drafting a resolution. Returns articles ranked by relevance, each with its id, title, a highlighted snippet, and updatedAt: search uses AND semantics, so every word in the query must match. [free]

  ConnectorNo auth

• search_notesA

  NoteMCPA

  Search the user's notes. Words are matched against the note's text, its tags, and the title, description and URL of any link saved with it; a word of three characters or fewer counts only as a whole word. The default mode ("auto") escalates only as far as it needs to: every word, then any word, then meaning — and the reply's `matched` field says which one answered, so a relaxed or semantic result is never mistaken for an exact one. Pin the strategy with mode="keyword" (every word must appear; never widens), "semantic" (meaning only) or "hybrid" (both, fused). Source, date, photo and thread filters compose with the text query and tags. Filter by tag with `tags`, which is the right tool for a request like "my #bug notes". An empty result carries `hints`: what the collection actually contains and which query to try next — read them instead of guessing another wording. Bodies are omitted unless you pass full=true; complete imported source metadata is omitted with them. Compact notes come back as { id, label, user_text, tags, source, root_id, parent_id, is_thread_head, thread_count, updated_at, … }. `user_text` is only text deliberately written by the user; imported page or social-post copy is source metadata. `label` names the note even when it has no title — use it when showing a note to a human. `updated_at` is what you pass back as `if_updated_at` when you write.

  ConnectorOAuth

• ol_federal_contractsA

  Oxford LedgeA

  Federal-contract obligation history for a ticker, OR the fiscal-year leaderboard -- for government-revenue-dependence diligence. TWO SHAPES: one of `ticker` or `fiscal_year` is REQUIRED (if both, `ticker` wins). With `ticker`: per-fiscal-year obligations (USD, the ten largest recipients, dropped_unresolved), NEWEST FY FIRST; with fiscal_year only: a leaderboard of the public companies on Oxford Ledge's USAspending crosswalk, largest first -- not of all federal contractors. A fiscal year still in progress is PARTIAL (period_complete false) and year-to-date -- never compare it to a full year. Obligations are federal awards, not company-reported revenue. `limit` default 20, hard cap 100. An unreachable store is REFUSED (DATA_UNAVAILABLE). Source: USAspending.gov (public domain; OL ticker-crosswalked); FREE. Attributing awards to a ticker is an Oxford Ledge curated crosswalk. Caveats ride the response's tool_notes.

  ConnectorNo auth

• openlibrary_get_workA

  openlibrary-mcp-serverA

  Fetch a work by Open Library Work ID (OL…W). Returns title, description, subjects, cover IDs, and linked author IDs for follow-up lookups. Works represent the abstract book concept independent of any specific edition. A merged work ID resolves to the work it was merged into. To reach a work from an ISBN, call openlibrary_get_edition with id_type "isbn" — its work_id output is the parent work. Note: author names are not included — use openlibrary_get_author or openlibrary_search_books for names.

  ConnectorNo auth

• SearchInvestmentAdvisersA

  equiblesA

  Search the tracked SEC Form ADV adviser set by firm name. Search first requires every punctuation-independent query word anywhere in the legal or business name, then broadens to any word only when no strict row matches. Returns CRD, main office, regulatory assets under management, employee count and as-of date, largest by assets first. Use the CRD with GetInvestmentAdviser.

  ConnectorNo auth

• SearchEconomicIndicatorsA

  equiblesA

  Search the curated set of ~40 US macro FRED series Equibles tracks (rates, inflation, employment, GDP, housing, market indicators) — not the full FRED catalog. Search first requires every punctuation-independent query word anywhere across the series ID, title, or category, then broadens to any word only when that strict search has no rows. Standard names such as fed funds rate, jobless claims, payrolls, yield curve, and core CPI are recognized. An empty query lists every tracked series. Results include seasonal adjustment, the latest observation date, and the UTC time Equibles last synced the series.

  ConnectorNo auth

• search_trademarksA

  GleanMark Trademark SearchA

  Searches USPTO trademarks by name (14M records) and returns the closest whole-mark matches, ranked by similarity and prefix. It is not an exhaustive contains-search: multi-word marks that only contain the queried word rank low and are often cut (a KWIK query can miss KWIK REWARDS or KWIK KOPY); search_marks_by_pattern returns complete lists. A short result does not show that a name is absent from the register or available.

  ConnectorNo auth

• get_word_of_the_dayA

  Vocab VoyageA

  Use this when the user asks for today's word, a daily vocabulary nudge, or a single-word warmup. Returns today's deterministic Word of the Day (definition, part of speech, example, synonyms/antonyms), optionally scoped to a test family (isee, ssat, sat, psat, gre, gmat, lsat, general). Do not use for arbitrary lookups — call get_definition instead.

  ConnectorNo auth

• ourairports_search_airportsA

  ourairports-mcp-serverA

  Search the bundled OurAirports corpus by free-text (name / municipality / keywords) and/or facets (country, region, type). Every query token must match (word order and partial words are handled). Returns ranked airport summaries — operational and larger airports first — each with its full code set and coordinates, ready to chain into ourairports_get_airport. Closed airports are excluded unless include_closed is set. Use ourairports_list_countries for valid country/region codes. For "nearest airport to a coordinate" use ourairports_find_airports instead. OurAirports is community-edited — not authoritative for flight operations.

  ConnectorNo auth

• interlinearA

  orthotomeoA

  Returns a row-aligned reading view for every word in a verse (or one word, if word is given): original text, transliteration, gloss (via lexicon_lookup), grammar, and manuscript attestation stacked per word - the composed display shape for a study reading view, built on parse and lexicon_lookup rather than any new query. This is the most complete per-word view; use parse or attestation when you want only one of those facets.

  ConnectorNo auth

• check_citationsA

  pubscopeA

  Verify a pasted reference list (plain text, BibTeX or RIS) against Crossref, OpenAlex, DataCite, Semantic Scholar, arXiv, PubMed and DBLP, plus Retraction Watch. Flags references that cannot be found (possibly fabricated), retracted papers and DOI mismatches. One check per day without an account; sign in for more.

  ConnectorNo auth

• search_meetingsA

  archiveA

  Which of the 1,422 published town meeting documents contain a word — every board, 2025 onward. Returns the board, the date and a citable URL for each. AN EMPTY RESULT MEANS THE WORD IS NOT IN THE INDEXED DOCUMENTS, which is not the same as nobody having said it: the archive starts in January 2025. It matches words exactly, so plurals are separate terms — search "jersey" and "jerseys" both.

  ConnectorNo auth

• entity_name_searchA

  NansenA

  Search Nansen's entity names by a partial name and get back the exact entity names that match. Use this when a tool needs an exact entity name and the user gave an approximate one (e.g. "binance" -> "Binance 14"). Matching is case-insensitive and matches anywhere in the name. For tokens or addresses use `general_search` instead.

  ConnectorNo auth