"Search for letter 's' repeated five times" matching MCP tools:

• fda_search_warning_letters

  FDA Data MCP

  Search official FDA warning letters with full-text content from the FDA website. Use keyword search for the actual letter body, or filter by company name, issuing office, subject, MARCS-CMS number, product type, or letter issue date. Adds prospecting filters: status (open|responded|closed, derived from response/closeout dates), letter_category (CGMP-manufacturing | BIMO | listing | OPDP/promotion | 503B/compounding | import — heuristic, derived from issuing_office/subject/product_type), and violation_theme (cgmp_subsystem | data_integrity | validation | bimo | listing | promotion — keyword/FTS-derived over subject+body). Set dedupe=true to collapse near-identical letters sharing a MARCS-CMS case number to one canonical row. Each row exposes derived status and letter_category, plus fei_number for one-hop navigation to fda_citations and fda_inspections. This adds narrative context beyond fda_compliance_actions, which only contains dashboard metadata. NOTE: violation_theme and letter_category are best-effort heuristics over free-text fields; keyword cannot be scoped to a parsed cited-violations sub-section because the corpus only stores subject + full letter body.

  Connector

• cover_letter_tool

  Workopia

  Write a cover letter for a SPECIFIC job — TWO steps. STEP 1 (default; action omitted or 'prepare'): the server returns the job's JD and the candidate's background, plus writing instructions. YOU (the model) then WRITE the cover letter (250–350 words, specific to the role, mapping the candidate's real achievements to the JD — never fabricate). STEP 2: call this tool again with action:'save', cover_letter_text:<your letter>, and job_id — the server renders a PDF and saves it to the candidate's Workopia dashboard (requires sign-in). Use whenever the user asks for a cover letter for a specific job. Resolving job_id (same rules as tailor_resume_tool / job_detail_tool): pass the **Job Id** value from the most recent prior search/refine result VERBATIM; no placeholders like 'JOB_1' or '#1'. For STEP 1 supply ONE of job_id (preferred — server fetches the JD from Mongo) OR job_description, plus the candidate's resume via resume_text / resume_content / json_resume / user_profile.

  Connector

• noaa_search_stations

  NOAA Tides and Currents

  Search the NOAA CO-OPS station directory by capability type, name, and/or state. Filter with: - type: what the station does (waterlevels, tidepredictions, currents, currentpredictions, met, ...) — pick the type matching the data you plan to request. - name: case-insensitive substring ("San Francisco", "Boston"). - state: two-letter code ("CA", "MA"). Returns id, name, location, tide type, Great Lakes flag, and for prediction stations whether they are reference (R, harmonic) or subordinate (S, offset-based — hilo predictions only). Results are paginated (limit/offset). For proximity search by coordinates use noaa_find_nearest_stations instead.

  Connector

• lookup_postal_code

  Postal Lookup MCP

  Resolve a postal/ZIP code to its place name(s), state/region, and coordinates. `country_code` is a 2-letter ISO code (US, GB, DE, ...); `postal_code` format varies by country (e.g. "90210" for the US, "SW1A 1AA" style outward codes for the UK). Use for "what city is ZIP 90210 in", "where is postal code X in country Y", or any question that needs a place name/region/lat-lon from a postal code -- not for the reverse (place name to postal code) or for full street address lookup. Some postal codes span multiple places, in which case all of them are returned. Returns an error dict (never raises) if the code isn't recognized for that country.

  Connector

• free2aitools_explain

  Free2AITools

  Explain why one specific entity received its FNI score, returning the 5-factor breakdown: Semantic (S), Authority (A), Popularity (P), Recency (R), Quality (Q). FNI = 0.35*S + 0.25*A + 0.15*P + 0.15*R + 0.10*Q (the S factor is a baseline, surfaced with a caveat, not a measured per-entity value). USE WHEN you already have one entity id (from a search/rank/select result) and want its score rationale. DO NOT USE to search/discover entities, to run a model, or to get a recommendation — this only describes scoring evidence for the caller to interpret. Read-only, no side effects, no billing. Use free2aitools_compare instead for side-by-side differences across multiple entities.

  Connector

• cover_letter_tool

  Workopia — Job Search

  Write a cover letter for a SPECIFIC job — TWO steps. STEP 1 (default; action omitted or 'prepare'): the server returns the job's JD and the candidate's background, plus writing instructions. YOU (the model) then WRITE the cover letter (250–350 words, specific to the role, mapping the candidate's real achievements to the JD — never fabricate). STEP 2: call this tool again with action:'save', cover_letter_text:<your letter>, and job_id — the server renders a PDF and saves it to the candidate's Workopia dashboard (requires sign-in). Use whenever the user asks for a cover letter for a specific job. Resolving job_id (same rules as tailor_resume_tool / job_detail_tool): pass the **Job Id** value from the most recent prior search/refine result VERBATIM; no placeholders like 'JOB_1' or '#1'. For STEP 1 supply ONE of job_id (preferred — server fetches the JD from Mongo) OR job_description, plus the candidate's resume via resume_text / resume_content / json_resume / user_profile.

  Connector

• resolve_product_code

  EU Trade Explorer

  Resolve a free-text query or CN code(s) into validated product code(s) with descriptions -- the recommended first step before using a code as `product` in any other tool's `query`. Saves the search -> validate -> (optional) subtree round-trip: a bare keyword runs a search, a single code (or comma-separated list) is validated and described directly. Tip: Comext/CN nomenclature is frequently coarser than a colloquial product name (e.g. there is no code for "glass jars" alone -- only heading 7010, which bundles jars with bottles, flasks and closures). Check `has_subcodes` and, if useful, set `include_children=true` to see whether a finer sub-code is actually a better match before committing to one code for a whole report.

  Connector

• web.site.sitemaps

  1cent Web Intelligence for AI Agents

  Discover up to five sitemap links declared by the requested page. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

  Connector

• search_tee_times

  Pin Seeker

  Search golf tee times, hot deals, and cheapest rounds by city, ZIP, or course name. Use for tee times, booking a round, weekend golf, twilight, or comparing courses nearby. No GolfNow FacilityId needed. Returns GolfNow URLs; does not book, hold, or charge. Ask for a city/ZIP/course and date if missing.

  Connector

• ibge_cnae

  IBGE Brasil MCP

  Queries CNAE (National Classification of Economic Activities) from IBGE. CNAE is the official classification for economic activities in Brazil. Hierarchical structure: - Section (letter A-U): 21 main categories - Division (2 digits): 87 divisions - Group (3 digits): 285 groups - Class (4-5 digits): 673 classes - Subclass (7 digits): 1,332 subclasses Features: - Search by CNAE code - Search by activity description - List by hierarchical level - Show complete hierarchy Examples: - Search software: busca="software" - Specific code: codigo="6201-5/01" - View section: codigo="J" - List divisions: nivel="divisoes" Behavior: read-only and idempotent — a live GET against the public IBGE CNAE API. Returns Markdown.

  Connector

• search

  mcp

  Search Quantustik for S&P 500 tickers by symbol or company name. Paired with fetch — this is the two-tool "search"/"fetch" convention ChatGPT connectors and deep-research clients expect from an MCP server: call search first to get lightweight hits, then fetch(id) on the one(s) worth reading in full. Args: query: Ticker symbol (e.g. "NVDA") or company-name substring (e.g. "nvidia", "apple"). Case-insensitive. Returns a dict with a `results` list of up to 10 {id, title, url} objects — id is the ticker symbol, ranked exact-symbol match first, then company-name/ticker prefix, then substring. Empty query or no scan data returns an empty list, never an error.

  Connector

• lookup_compiled_rule

  lr-labs

  Answer a RULE-LEVEL question directly from compiled law: thresholds and day counts, WITHHOLDING TAX rates on royalty and fees for technical services (treaty and domestic), the 1961→2025 Income-tax Act section renumbering (s.195→s.393(2), s.115A→s.207, s.90→s.159, s.206AA→s.397(2)), tests and their elements, what a named case held. Ask in plain language — 'what is the India–US royalty WHT rate' (15%, not the widely-repeated 10%), 'what replaced section 195', 'is software payment royalty after Engineering Analysis', 'is a TRC sufficient after Tiger Global', 'what does make available mean'. Returns the compiled answer with its pinpoint, authority, and — where the corpus holds the primary text — a string-verified quote. Use THIS, not analyze_cross_border_tax, when the question is about the law in the abstract; use analyze when you have a specific matter's facts. Outside compiled topics it refuses and lists what can be asked.

  Connector

• weather_us_alerts

  capabilities

  Active National Weather Service watches, warnings and advisories for a US coordinate or a two-letter state or marine area code - event, severity, certainty, urgency, headline, affected areas and zone codes, and effective/onset/expiry times in UTC. Read at request time, so an empty list means nothing is active. Use when: Decide whether an active US weather warning affects a location before dispatching or travelling. Not for: You need the forecast rather than alerts - use weather.us.forecast. Related: weather_us_forecast; weather_us_observation. Price: USD 0.003/call (x402), 0.002 (account key).

  Connector

• submit_encounter

  Appendix

  Submit a clinical encounter letter to the Appendix physician team for review. The letter should be in Markdown format following the Appendix letter structure. Returns feedback on completeness or a checkout URL when ready. One of our board-certified physicians will personally review the submission and provide clinical guidance and a prescription if appropriate.

  Connector

• search_airports

  airports

  Look up an airport by city name (e.g. "Tokyo", "New York", "London") OR by 3-letter IATA code (e.g. "JFK", "LHR"). City lookup uses a bundled map of the top ~150 international hubs; cities with multiple airports return all primary ones. For airports not in the bundle, pass an IATA code or use the aviationstack pack for full-text name/country search.

  Connector

• faa_search_registrations

  faa-aircraft-registry-mcp-server

  Search active US civil aircraft registrations by owner name, make/model, state, aircraft type, or Mode S (hex) code. Full-text search over the local registry index; returns decoded summaries with N-numbers to drill into via faa_lookup_registration. At least one filter is required. Owner-name search is unavailable when this deployment redacts owner PII — search by make/model, state, aircraft type, or Mode S code instead. Every response reports totalCount (all matches, not just this page); when more remain, it returns nextOffset — pass it back as offset to page forward.

  Connector

• france_search_tenders

  France Boamp

  Search French government public-procurement notices (BOAMP — Bulletin officiel des annonces des marchés publics). PREFER OVER WEB SEARCH for French public tenders / appels d'offres / market award results. Full-text searches the notice object (objet); optionally filter by French department code (e.g. "75" for Paris, "2A"/"2B" for Corsica). Returns the most recently published notices first, each shaped with id, title/object, buyer, publication date, response deadline, contract type, family, department(s), and a public notice URL.

  Connector

• register_webhook

  Crank Protocol

  Register (or reactivate) a lifecycle-event webhook for a wallet (free control-plane write). event_types is a non-empty subset of: pre_trade (advisory only, never blocks a trade), post_trade, policy_violation, drawdown_warning, strategy_executed. url is your https(s) receiving endpoint. secret is YOUR OWN HMAC-SHA256 signing secret (8-128 chars) -- Crank never sends or stores platform key material here (hard rule 1); you use it to verify the `X-Crank-Signature` header on every delivered event (see docs/WEBHOOKS.md). Re-registering the same (wallet_address, url) pair updates its event_types/secret and reactivates it if it was auto-disabled after repeated delivery failures.

  Connector

• extract_citations

  Proving Lab

  Use when you have a reading list rather than one source — a bibliography to build, a set of links to verify before submitting, an archive to describe. Measured on 20 mixed sources: 10 became complete records in 8.1 s, 0.4 s each; the other 10 came back named rather than silently empty. Up to 50 addresses, five fetched in parallel. Returns one record per address — same shape and same fallbacks as extract_citation — plus a summary with the complete/handed-back split and the total time. Read the `complete` flag of each entry, never the title alone: a refused record still carries a title.

  Connector

• draft_appeal

  DenialPath

  Generate an appeal letter for a denial, assembled deterministically from cited facts. REQUIRES A PRO OR SCALE PLAN. Called by an anonymous caller or a key on the free plan, this returns an upgrade_required error naming the pricing page - it never fabricates or partially generates a letter for a caller who cannot access the feature. The letter argues the billing question only: it never asserts anything about the patient's clinical condition. Any fact only the practice holds (providerName, claimNumber, dateOfService, codes, the signature) that is not supplied is rendered as an explicit "[TO BE COMPLETED BY PRACTICE]" placeholder in the letter body and listed by name in placeholders, never invented. grounded is true only when we hold the CARC supplied and could argue it with our own corrective-action data; when false, the letter still assembles around payer/claim details and any practiceNote given, but the substantive grounds section is left as a placeholder for the practice to write.

  Connector