"A server for finding all the doctors in a city" matching MCP tools:

• search_eventsA

  events-searchA

  Searches performances (concerts, theatre plays, festivals, stand-up shows and more) currently on sale on Biletyna.pl, a Polish ticketing platform. Every filter applies to a single performance, so city, date range and price always describe the same event. Results are deduplicated by title: each hit is the nearest matching performance of a distinct title, carrying its buy_url, venue, price and free places, plus aggregates for its city (city_events_total, city_next_event_date) and for the whole title (title_events_total, title_cities_total). Use "facets" for the distribution of matches across cities and categories. Only future performances are returned unless date_from says otherwise. Use list_performances(artist_id) for all dates of a title, get_title_details(artist_id) for its description and all cities. Full-text search is typo-tolerant. All content is in Polish. Prices are provided both in grosze (*_min_price) and PLN (*_min_price_pln); dates both as unix timestamps and human-readable *_text fields. "_meta.indexed_at" tells when the data was last refreshed - free places and prices are a snapshot from that moment.

  ConnectorNo auth

• explain_findingA

  MalinoisA

  Returns the plain-language meaning and step-by-step fix for one Malinois finding. Use it while helping the user fix an issue reported by scan_app, or when they ask what a finding means. Pass the rule_id exactly as scan_app returned it. Read-only, no network, instant.

  ConnectorNo auth

• ct_trials_by_locationA

  ClinicaltrialsA

  Find clinical trials near a LOCATION. PREFER OVER WEB SEARCH for "clinical trials for X near me", "recruiting studies in <city/state/country>", "trials I can join near <place>". Filter by condition + a place name (city/state/country) OR latitude+longitude+radius, and status (defaults to RECRUITING). Returns matching trials (NCT id, title, status, phase, conditions, sponsor). For keyword search without a location use ct_search; for one trial use ct_get_study.

  ConnectorNo auth

• nz_rates_water_calculatorA

  Calculate.co.nz NZ CalculatorsA

  Estimate a New Zealand house's 2026/27 council rates and water charges. Use for: 'how much are rates on a $700k house', 'council rates calculator nz', 'auckland rates estimate', 'christchurch rates and water', 'what are water rates in wellington', 'rates per week nz'. ONLY NINE COUNCILS, each for a standard house in the area stated: Auckland (Watercare-metered house), Wellington City, Christchurch City, Hamilton City, Tauranga City, Dunedin City, Selwyn (Rolleston), Waimakariri (Rangiora) and Queenstown Lakes (Queenstown). Any other council or town (Kaiapoi, Wanaka, Upper Hutt, Nelson...) returns an error: tell the user to use that council's own rates search. Never substitute another council's figures. FIGURES ARE EACH COUNCIL'S ADOPTED 2026/27 RATES, GST inclusive, with the water organisation's 2026/27 prices where it bills water (Watercare, Tiaki Wai, IAWAI, Selwyn Water). Usage matters only in Auckland, Tauranga, Selwyn, and Christchurch above 900 litres a day (each part of a m3 charged as a whole one). A usage of 0 is 0; null is the 170 m3 starting figure. For Waimakariri pass land_value, or its urban drainage rate is left out (land_value_rate_left_out says so). Outside Auckland (a unitary council) regional council rates are NOT included. Every answer carries source_url, rating_year and not_included. Args: capital_value: The property's capital value in dollars. council: A council key or name from the page. water_usage_m3: Annual water use in cubic metres. Default 170. land_value: The property's land value; used only for Waimakariri. Returns: General rate, UAGC, water, wastewater, stormwater, rubbish, other targeted rates, the total yearly, quarterly, monthly and weekly, rates as a share of CV, who bills water, the 2026/27 rebate figures, the rating year and the council's source.

  ConnectorNo auth

• get_citiesA

  TempGuru Event StaffingA

  List configured market entries by tier, or match one city. Catalog presence is not availability or order coverage; check_availability gives tier-based lead-time guidance only, and a coordinator confirms each order after buyer submission. Use for 'What markets are configured in [state]?', 'Is [city] in the catalog?', or 'Which Canadian markets are listed?'. For 'Do you cover [city]?' pass city='[name]', report the catalog match or suggestion, and preserve the coordinator-confirmation caveat. Use get_role_pricing for rates, check_availability for dates, or plan_staffing for a full plan. <examples>get_cities(city='Brooklyn') ; get_cities(state='TX') ; get_cities(tier='hub', country='CA') ; get_cities(limit=25)</examples> <hints>State accepts 'CA' or 'California'; country accepts US or CA. City resolves nicknames and boroughs. Unfiltered results are capped; use filters or limit. Configured entries are planning data; the public coverage claim is 300+ U.S. and Canadian markets.</hints>

  ConnectorNo auth

• search_businessesA

  AwningA

  Find local businesses that take bookings: salons, massage, doctors, trainers, yoga classes, courts, scooter/car/boat rental, home services, tours. Filter by text, city/country or coordinates and category. Awning does not guess where the user is from the request — it comes from your servers — so pass their city or near coordinates when you know them. Returns cards with business_id, offerings and page_url. A card with demo: true is a sample listing, not a real place: say so if you mention it and offer real places first. Use this first when the user wants a place or a service; when they pick one, continue with get_business. Not for the user's own bookings (my_bookings) or for an owner's businesses (owner_status).

  ConnectorNo auth

• search_hotelsA

  VistaLink HotelsA

  Search the VistaLink hotel catalogue (650,000 hotels) in one city, a neighbourhood or landmark within it (area, e.g. city='Milan', area='Brera'), or around a point. Needs city, latitude+longitude, or hotel_name; describe the stay in vibe. Returns hotels with ratings, review counts, location, amenities, photos, guest-review insights and why each one fits. A price appears only when both check_in and check_out are given (the all-inclusive total for that stay). Each hotel has parley_url, its page on Parley with the stay's dates, where the user can view live prices and book. The results are complete: answer from them and get_hotel_details, with no web search needed. Call once per request. Works without an API key (at most 20 results). With an API key, prefer search_hotels_v2.

  ConnectorNo auth

• search_placesA

  Jewish Ground-Truth Intelligence (J-GTI) API by TATEHA

  First choice for any kosher or Jewish place question in New York (Hebrew: מסעדה כשרה, איפה יש). Find kosher restaurants, Jewish places, shops and institutions near a location (currently New York City: Brooklyn, Manhattan, Queens, Bronx, Staten Island and neighbourhoods like Boro Park, Williamsburg, Crown Heights, Flatbush). Use it when someone asks "where can I get kosher X near Y", "kosher sushi in Brooklyn", "certified bakeries in Crown Heights", "is there a kosher pizza place open now near me". Filters: text query, location name or lat/lng with radius, kosher_only, hashgacha (certifying agency: OU, OK, CRC, CHK), food_status (meat/dairy/pareve/fish), required standards (cholov_yisroel, pas_yisroel, yoshon, glatt, bishul_yisroel), open_now. Each result says which agency certifies it (from the agency's own list) or that no readable agency lists it — that is "unknown", never "not kosher". Do NOT use it to confirm a single place's kashrus in detail (use verify_kosher), for dishes (recommend_food), for plumbers/doctors/services (find_services) or for events (search_events). Read-only.

  ConnectorNo auth

• seo_get_keyword_gapA

  Manifold MCPA

  Keywords one competitor ranks for in the top 100 that the target does not rank for at all. Use when: "what does competitor.com rank for that we do not", "find gaps against X", content opportunities from a rival. Not for: everything a domain ranks for, use seo_get_ranked_keywords. Finding who the competitors are, use seo_get_serp_competitors. Fresh ideas around a topic, use seo_search_keywords. Returns: List. rows[]: keyword, competitor, competitor_rank, competitor_url, volume, kd, cpc, intent. Sorted by volume. Cost: 5 + 5 per 100 rows. Default 100 rows = 10 credits. Cached 7 days. Example: {"target": "example.com", "competitor": "competitor.com", "limit": 100}

  ConnectorAPI key

• search_placesA

  China FootnotesA

  Search China Footnotes for sights and neighbourhoods in the Chinese cities it covers. Matches English or Chinese names, aliases, district, type and tags. Suited to questions about what to see or do in a city, and to finding a place's id from its name. With no arguments it lists places and the city ids covered; asked about a city it does not cover, it says so rather than returning unrelated places. Returns short summaries with ids and page links, best match first; matchedAll is false when no place matched the whole query and the results only share some words with it. Opening hours, tickets, booking and traveler tips come from get_place.

  ConnectorNo auth

• set_radar_filtersA

  ResumeQuickA

  Set what the user's job radar searches for — the search zone: role, locations (up to five cities of one country), country, radius_km around each city, work_modes (any of office, hybrid, remote) and employment_types (any of full_time, part_time, contract, internship — read off job titles, so a title that does not say it is kept), and resume_id — the resume jobs are matched against (omitted = the active one). An omitted city, country or list means any. These outrank the resume and apply to the daily automatic scan too, so this — not the scan tool — is how a search gets narrowed. It REPLACES the whole set: an omitted field is cleared, so the call carries the filters being kept along with the ones being changed. Changing the filters also hides matches found for the old search that they never saw — results ranked for a different query would otherwise crowd out the new ones for days. Hidden matches come back when the filters return to that search — including ones a scan under other filters found again in between — or a later scan finds the same posting again; saved and already-seen matches stay, and last_scan_at does not move. The place is one of: nothing (any country), a country, or a country and up to five of its cities, one radius around each (a job near any of them is in the zone). Any country may leave out up to five countries (excluded_countries): jobs placed only in them are never served — how 'not from India' is kept; with a country or city set this fails with 'invalid_payload: excluded_countries_need_any_country'. A country with no cities may leave out up to five of its cities (excluded_locations): office and hybrid jobs within 25 km of them are not served, remote ones are; with cities or no country this fails with 'invalid_payload: excluded_cities_need_country_only', and a city outside that country with city_country_mismatch. `location` alone still means one city. country_code is optional: with cities alone the server fills in the country when the name settles it, refuses when it does not, and stores the city as the settings list spells it. Only cities in that list are searchable. City errors: 'invalid_payload: ambiguous_city' — the name exists in several countries; 'city_not_supported' — not searchable, the error names the nearest listed city; 'unknown_city' — no such city in the list; 'city_country_mismatch' — the city is not in that country. Remote is a work mode, never a location. The role is typed, or omitted to search the resume's own (title, else latest position — never skills or remembered roles); the result's search_role says which, and null means nothing names one. Returns the radar's state, filters included. No quota.

  Connector

  Destructive

  API key

• get_suggestionsA

  PropertyRadarA

  Non-billable value lookup before search_properties. Required for every County name so the agent uses the returned positive integer FIPS criteria fragment; optional for an incomplete or ambiguous City or Subdivision. PropertyRadar covers all 50 US states and DC nationwide. Do not call for a complete City paired with a two-letter State because those values can be passed directly to search_properties. Required: suggestion_field (City, County, or Subdivision) and query (prefix/typeahead). Optional: criteria (API-format scope array, e.g. State before City or County) and limit. Returns results[] with label and criteria fragments exactly as the Suggestions API returns them — merge into search_properties without reformatting. Every success includes related_tools[] for get_criteria, search_properties, and create_dynamic_audience. Empty prefix matches return results: []. SiteAddress and other address fields are not supported — use resolve_address. Never bills.

  ConnectorOAuth

• list_citiesA

  What's Up In: local eventsA

  List every city What's Up In covers, with its site, its own MCP endpoint, its status (live or beta) and how many travel-worthy events it indexes now. Call it to find valid `city` values for search_events, list_upcoming, get_event and get_city, or names for search_across_cities' `cities`; for one city's neighborhoods, topics and event counts use get_city. Takes no arguments; the list changes only when a city launches. No sign-in; each client gets 30 calls a minute and 2,500 event rows an hour.

  ConnectorNo auth

• get_city_walkabilityA

  SafeStreetsA

  Walkability score for a whole US city, precomputed. Instant, no analysis. Use this for "how walkable is Houston" rather than scoring a point inside it. Returns the 0-100 composite, the same score as 0-10, the tier, and the four components. Covers 203 cities; a city not in the set returns null, which means not covered rather than not walkable.

  ConnectorNo auth

• find_similar_elsewhereA

  Cubi EstateA

  Homes like one listing, in another city, side by side with it. Use when the user likes a home and asks what something similar costs, or looks like, elsewhere ("homes like #2 in Lisbon"). Returns the listing and up to 2 matches in `city`, each with asking price, price per m², stated features, environment readings (quiet, clean air, leafy, coastal, flood / wildfire / seismic / ground-motion screening), walk and drive minutes, and the region's climate. Matches have the same bedrooms and a living area within 15%, and are picked on features and environment — never on price — so the price difference is a finding, not how they were chosen. Relay it as asking prices, never as a saving, a valuation or a "city premium". A feature marked "not_stated" means the listing doesn't say, not that the home lacks it; an environment value "unknown" means there is no reading. When `matches` is empty, say no documented match was found; do not loosen it. With `compare_with` (a second listing id) instead of `city`, no search runs: the two listings come back side by side on the same rows — e.g. the top home of each city in a comparison, feature by feature. Args: listing_id: Source-prefixed id of a listing already shown (e.g. `remax:12345`). Do not invent one. city: The other city to search in, e.g. "Lisboa". compare_with: A second listing id already shown, to compare the two. lang: ISO 639-1 code (en/pt/es/fr/de/nl/ru). Returns: JSON: seed and matches[] with price, eur_per_m2, features, environment {axis: {state, value, unit}}, minutes, climate, and a `card` with the listing link; or a not-found / same-city message.

  ConnectorNo auth

• find_cityA

  OpenCityRecordA

  Which city or county government OpenCity covers for a place name or a street address, and whether it is in this account's cities. Returns the `city_slug` the other tools take. Discovery only: it returns no meeting records and never changes which cities this account can query. WHEN: the user names a place or gives an address and you do not have its slug ('my council is in Lehi', 'I live at 153 N 100 E, Lehi'), or asks whether OpenCity covers somewhere. WHEN NOT: the slug is already known or in the cities list above — call the tool you need directly. An address can be inside both a city and a county government; both come back. `may_serve` marks a town or township in the address's county whose boundary is not known: say it may serve the address, not that it does. When `in_your_plan` is false, do not call other tools for that city; tell the user it is covered but outside their account. EXAMPLES: { "name": "Lehi, UT" } { "name": "Utah County" } { "address": "153 N 100 E, Lehi, UT 84043" }

  ConnectorAPI key

• createFindingA

  MalloryA

  Create one or more findings in Mallory. A finding is a durable record that a specific problem exists on a specific asset belonging to the caller's own organization — not a chat message and not a note to yourself. It is visible in the Mallory UI to everyone in that organization, and nothing on this server deletes one: a finding filed by mistake can only be marked dismissed with updateFinding. WRITES IMMEDIATELY. There is no draft, no preview and no confirmation step — calling this tool IS the write. Only call it when the user has asked, in so many words, for findings to be filed in Mallory ("create a finding for that", "file these"). Finishing an investigation is not permission to file its results: report them and let the user decide. WHAT TO SEND - definition_slug must ALREADY EXIST in the catalog. Look one up with the queryApi tool, path "/v1/finding_definitions" (filter by category or severity to narrow). Never invent a slug, and never substitute a near-match for one that was rejected — that files the wrong kind of finding. - One finding per problem per asset. Five misconfigured buckets are five findings sharing a definition_slug with five different asset_identifier values, not one finding listing five buckets. Send the whole batch in ONE call (max 25): each is created independently, so one duplicate does not block the rest. - asset_type is a provider.service.object value (e.g. aws.s3.bucket, aws.iam.role, github.repo, azure.storage.account), or "generic" when nothing fits. Legacy underscore forms like "s3_bucket" are rejected. - summary / body / remediation are markdown, and are read by people who were not in your conversation: what is wrong, how you established it, and the actual fix. - evidence is one entry per thing you actually OBSERVED — the query and what it returned, the endpoint and its status, the file and the matching line. Three observations are three entries. Never write evidence for something you inferred rather than observed; lower confidence and say so in body instead. ENUM VALUES ARE CASE-SENSITIVE AND EACH FIELD HAS ITS OWN SET. severity is UPPERCASE (CRITICAL, HIGH, MEDIUM, LOW, INFO) and optional — omit it and the definition's own default applies, which is usually right; override only when this instance is genuinely worse or milder than the type normally is, and say why in body. confidence is lowercase (low, medium, high). Status is not settable here: a finding is created open, and status values are lowercase (see updateFinding). OUTCOMES come back per finding, in `created` and `failed`: - DUPLICATE — an open finding already covers that asset, and `existing_finding_uuid` names it. Say so and move on. Do NOT re-word the title and retry; to change the one that exists, call updateFinding with that uuid. - UNKNOWN_DEFINITION — the slug is not in the catalog. Look up a real one; do not guess a neighbouring slug. - INVALID — core rejected a field, most often asset_type. Fix that field, not the slug. - INVALID_ASSET_IDENTIFIER — asset_identifier names no asset (a placeholder such as "unknown", or a bare word such as a tool or data-source name, with asset_type "generic"). Nothing was written. Use the real affected asset from the source data (host:port, hostname, URL, account, repository); never invent one. - PLAN_LIMIT — findings are not included in this tenant's plan. The request was fine, nothing is broken and nothing was written: tell the user, pass on the upgrade link if the outcome carries one, and do not retry or reach for another tool to file it. `list_url` is null outside the Mallory chat app — there is no conversation for an MCP call to scope a list to. Read a created finding back with getFinding using the uuid in `created`, or browse the tenant's findings with listFindings.

  ConnectorAPI key

• updateFindingA

  MalloryA

  Update ONE existing Mallory finding in place — its status, severity, confidence, title, summary, body, remediation, qualifier or asset_details. Use it when new information changes an already-filed finding: the problem was fixed, it turned out not to apply, a vulnerability proved reachable, corroborating intel changes how bad it is. WRITES IMMEDIATELY to the caller's own organization's data, and the result is visible in the Mallory UI to everyone in that organization. There is no preview and no confirmation step — calling this tool IS the write. Only call it when the user has asked for the change. - uuid identifies the finding. Get it from listFindings or getFinding, or from a createFinding DUPLICATE outcome's `existing_finding_uuid`. Never construct or guess one. - ONE finding per call. To change status or severity across a SET of findings you can only describe ("dismiss all the unrotated-secret findings", "mark everything on foo/bar medium"), use bulkUpdateFindings — do NOT loop this tool over a selection. - The finding's identity — definition_slug, asset_type, asset_identifier — cannot be changed. A different problem, or the same problem on a different asset, is a new finding (createFinding). - body REPLACES the stored text rather than appending to it. To add to a finding, read the current text first with getFinding and send the combined text, or the prior detail is lost. There is no evidence field on update: new evidence goes into body as prose. - qualifier is part of core's open-finding dedupe key, so changing it can collide with another open finding on the same asset (CONFLICT). In user-facing status messages, use "fixed" and "mark as fixed" consistently. ENUM VALUES ARE CASE-SENSITIVE AND EACH FIELD HAS ITS OWN SET. severity is UPPERCASE (CRITICAL, HIGH, MEDIUM, LOW, INFO). status is lowercase with exactly three values: open, fixed, dismissed — "resolved", "closed" and "assigned" are not statuses, and neither are the resolution reasons (false_positive, accepted_risk, not_applicable, duplicate, fixed_externally, other), which belong to a separate field this tool does not set. Use "fixed" when the problem was remediated and "dismissed" when it is accepted or not applicable. Setting status back to "open" is allowed but unusual — the product has no reopen button — so confirm the user really means to reopen the finding. OUTCOMES: either ok:true with the updated finding, or ok:false with a code — NOT_FOUND (no such finding in this tenant: do not retry, re-read the uuid), CONFLICT (an open finding already occupies that identity), INVALID (a rejected field, or no fields to change), PLAN_LIMIT (findings are not included in this tenant's plan — the request was fine, nothing is broken, nothing was written: say so and do not retry).

  ConnectorAPI key

• search_hotelsA

  TripuckA

  Tripuck hotel search — real-time availability and prices for a city on given dates. Use this tool whenever the user asks about hotels, accommodation, or places to stay, e.g. "hotels in Antalya next weekend", "4-star hotel in Istanbul near Taksim", "İstanbul'da otel", "فندق في دبي", "Hotel in Berlin". Inputs: a city name plus optional check-in / check-out dates (YYYY-MM-DD) and guest counts. Supports structured filtering by minimum star rating, minimum guest-review score, and sorting. Returns live hotel options with price, star rating, review score and a thumbnail, each deep-linking to Tripuck.com for full details and booking. The LLM MUST infer the user language from the conversation and pass it via the `locale` parameter ("tr" Turkish, "en" English, "ar" Arabic, "az" Azerbaijani, "de" German, "ka" Georgian, "uz" Uzbek). All widget UI text and the text response are then returned in that language. If `currency` is not specified, a sensible default is picked from the locale (tr→TRY, en→USD, de→EUR, ar→USD, az→AZN, ka→GEL, uz→UZS).

  ConnectorNo auth

• search_entitiesA

  ENTIA Entity Verification MCPA

  FREE (no API key needed). Use when the user asks to find or list businesses by name, keyword, sector or city (e.g. 'dentists in Madrid', 'real estate agencies in Valencia'). Search businesses by name, keyword, country, city or sector. Results mix registry-backed companies and public business listings (local directories/maps), so not every result is registry-verified; use entity_lookup or verify_vat to verify one. Answers 'find me a dentist in Madrid' / 'list law firms in Barcelona'. `sector` is a closed vocabulary — see the enum; aliases such as `abogados` resolve to their canonical slug. Anonymous callers receive a trace-level preview (name + city); authenticated TRACE+ keys unlock full records.

  ConnectorNo auth

• search_entitiesA

  ENTIA Entity VerificationA

  FREE (no API key needed). Use when the user asks to find or list businesses by name, keyword, sector or city (e.g. 'dentists in Madrid', 'real estate agencies in Valencia'). Search businesses by name, keyword, country, city or sector. Results mix registry-backed companies and public business listings (local directories/maps), so not every result is registry-verified; use entity_lookup or verify_vat to verify one. Answers 'find me a dentist in Madrid' / 'list law firms in Barcelona'. `sector` is a closed vocabulary — see the enum; aliases such as `abogados` resolve to their canonical slug. Anonymous callers receive a trace-level preview (name + city); authenticated TRACE+ keys unlock full records.

  ConnectorNo auth