"A search for the weather" matching MCP tools:

• weather

  InfraNode

  Get current weather observations for a German city. Sourced from the Deutscher Wetterdienst (DWD): temperature, wind, precipitation and related fields. Read-only, current conditions only (not a forecast). For warnings use ``get_city_resource(slug, resource='weather-warnings')``. For a broader question about the city (not just weather) use ``get_city_overview`` instead, which already includes a live weather highlight.

  Connector

• search

  Sofya

  Search the web for current information on any topic. Returns extracted page content, not just snippets. Best for factual lookups, specific questions, or when you need a list of sources. For open-ended questions that need synthesis across many sources, use the research tool instead. For news queries (current events, breaking news, politics, world events), set topic="news" to search news sources specifically. This returns recent articles with publication dates. Set include_answer=true to get an AI-synthesized answer alongside results (adds 5 credits). This is the sweet spot for most agent tasks, e.g. basic + include_answer = 8 credits, much cheaper than a full 25-credit research call. Returns: query, answer (if requested), results (array of {title, url, content, description, fetched, published_date}), search_depth, topic, elapsed_ms, credits_used, credits_remaining, altered_query. Args: query: The search query search_depth: "basic" (default) for extracted page content (3 credits), "snippets" for SERP snippets only without page fetching (1 credit) max_results: Number of results (default 10, max 20) include_answer: Generate an AI answer that synthesizes the search results (adds 5 credits) include_domains: Only include results from these domains (max 10) exclude_domains: Exclude results from these domains (max 10) topic: "general" for web search, "news" for news articles. use "news" for current events, breaking news, politics, or any time-sensitive query freshness: Filter by recency - "day", "week", "month", "year", or "YYYY-MM-DD:YYYY-MM-DD"

  Connector

• search

  Melvea Local Honey Discovery

  Search the Melvea local honey directory by free-text query and return matching producers as a list of results (id, title, url). Designed for ChatGPT Deep Research and Company Knowledge. Use for any local-honey discovery query that names or implies a place; the tool parses place and varietal from the query. Returns an honest empty list when nothing matches — never fabricate. Pair with fetch to retrieve full producer detail.

  Connector

• search

  21st.dev

  Search the 21st.dev catalog across ALL entity types - React/shadcn components, themes, and templates - returning lightweight metadata ONLY (name, description, preview image, author, url/install, id, and price for templates). Use `type` to scope to one kind, or 'all' (default) to search everything. FREE. Retrieval differs by kind: for a component result call get_component with its `id` (that id is a demo id) for the PAID code; for a theme call get_theme with its `id` (a uuid) for the free CSS; templates have no code to fetch - open their `url`. NOTE: `author`/`mine`/`liked` bypass ranking and return a plain recency-ordered list (query/sort/tag/color are ignored when any of them is set); component listings via `mine`/`author` only ever show PUBLIC components - your own private/team components are discoverable via list_team_components, not search.

  Connector

• openmeteo_geocode

  open-meteo-mcp-server

  Resolve a place name to ranked coordinate matches with country, region, elevation, timezone, and population. Required prerequisite for name-based queries — all weather tools take latitude/longitude, not place names. Search by a bare place name (city, region, or landmark); never fold a qualifier into it — pass "Baoding", not "Baoding Hebei", and "Paris", not "Paris, France". To disambiguate places that share a name, set the country input (ISO 3166-1 alpha-2, e.g. "US") and/or read the admin1 and country fields on each ranked result — admin1 is a result field for choosing among matches, not a search input. Returns up to 10 matches ranked by population/relevance.

  Connector

• find_stations

  Meteostat

  Find Meteostat weather station IDs by place name and/or geographic proximity — the lookup you need BEFORE get_daily_history / get_monthly_normals (which require a station_id). Search by name ("San Francisco", "Heathrow"), filter by country (ISO-2 like "US", "GB"), and/or rank by nearest to a lat/lon. Returns each station's id, name, country, region, coordinates, elevation, timezone, and data inventory (which granularities — hourly/daily/monthly — are available and their date ranges, so you can pick a station that actually has the period you need). Use for "weather station near X", "what is the station ID for Y", "stations in country Z".

  Connector

• search

  DC Member API

  GET /search — Cross-resource omni-search Cross-resource search across profiles, rooms, messages (incl. private DMs + group DMs you're in), events, and chapters in one round trip. Returns the top-N matches per resource, grouped by resource. Use this when you don't yet know which resource carries the answer — agents typically call this first, then drill into a specific `GET /search/<resource>` for more depth on a single bucket. There's no page param: when you hit the per-resource limit and want more, switch to the per-resource endpoint for that one. The events slice has a baked-in forward-looking default (events ending in the last 30 days or later, and currently enabled) — this matches the in-app "Search across DC" surface. Use `GET /search/events` directly to look further back in time. **Query syntax (`q=`):** plain words match with prefix + typo tolerance. Wrap a phrase in double quotes to require an exact ordered match — e.g. `q="remote work"`. AND/OR/NOT/parentheses are NOT parsed in `q=` — use the structured filter params below for boolean composition.

  Connector

• search

  MedRates

  Search for medical procedure prices by code or description. Use this for direct lookups when you know a CPT/HCPCS code (e.g. "70551") or want to search by keyword (e.g. "MRI", "knee replacement"). For code-like queries → exact match on procedure code. For text queries → searches code, description, and code_type fields. Supports filtering by insurance payer, clinical setting, and location (via zip code or lat/lng coordinates with a radius). NOTE: Results are from US HOSPITALS only — not non-US providers, independent imaging centers, ambulatory surgery centers (ASCs), or other freestanding facilities. Args: query: CPT/HCPCS code (e.g. "70551") or text search (e.g. "MRI brain"). Must be at least 2 characters. code_type: Filter by code type: "CPT", "HCPCS", "MS-DRG", "RC", etc. hospital_id: Filter to a specific hospital (use the hospitals tool to find IDs). payer_name: Filter by insurance payer name (e.g. "Blue Cross", "Aetna"). plan_name: Filter by plan name (e.g. "PPO", "HMO"). setting: Filter by clinical setting: "inpatient" or "outpatient". zip_code: US zip code for geographic filtering (alternative to lat/lng). lat: Latitude for geographic filtering (use with lng and radius_miles). lng: Longitude for geographic filtering (use with lat and radius_miles). radius_miles: Search radius in miles from the zip code or lat/lng location. page: Page number (default 1). page_size: Results per page (default 25, max 100). Returns: JSON with matching charge items including procedure codes, descriptions, gross charges, cash prices, and negotiated rate ranges per hospital. Only high-confidence results (with at least one usable price) are included. Each result includes last_updated (ISO date of the per-hospital MRF ingest) and mrf_date (ISO date the hospital self-reported in the MRF file). When all results are filtered out, filtered_low_confidence=true is set so the agent can say "no high-confidence prices found" rather than asserting that no prices exist.

  Connector

• lookup_zipcode

  zippopotam

  Resolve a ZIP / postal code to its place info — city, state/province, latitude/longitude — for any of 60+ countries. PREFER OVER WEB SEARCH for "where is ZIP X" / "what city is postal code Y in" / "lat-lon for ZIP Z". Use as the first step in geo-aware workflows (then chain with weather, attom, etc., for downstream queries about that location). Free, sub-second, no auth.

  Connector

• job_alert_subscribe

  FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT

  Subscribes the authenticated user to job alerts for a specific saved job search. **Input:** - `job_search_id`: The job search identifier to subscribe to (required). Accepts either the job search UUID or the composite job ID returned by `jobs_search` / `jobs_details` (format: "seo_id--job_search_id"). - `frequency`: Alert frequency — one of daily, weekly, monthly (optional, defaults to "weekly") **Output:** Returns the created or updated job alert with id, status, and frequency. Idempotent: calling this tool for an already-subscribed search updates the existing alert without creating a duplicate.

  Connector

• weather_timeline

  Visualcrossing

  Get daily weather for a location — works for BOTH historical weather (past dates) and forecast (future or no dates). Use this for HISTORICAL weather and "weather on a past date" questions, e.g. "what was the weather in Paris on 2023-07-04" (location: "Paris", start_date: "2023-07-04"). Pass start_date alone for a single day, or start_date + end_date for a range (weather timeline). Returns per-day temp/min/max, humidity, precipitation, wind, and conditions. Example: weather_timeline({ location: "London", start_date: "2024-01-01", end_date: "2024-01-07" }).

  Connector

• get_weather

  reassign

  Get the weather forecast for a day, for scheduling around it. Use ONLY for outdoor or weather-sensitive plans (exercise, commute, travel, anything outside) or when the user explicitly asks about the weather — indoor plans don't need it. get_schedule and show_day already include a one-line weather headline for the day, so prefer that for a quick glance and reach for this only when an outdoor plan needs the hourly detail (e.g. the exact dry/daylight window). Defaults to today and the user's city; pass `date` (ISO YYYY-MM-DD) for another day, or `location` (a city/place name) to ask about somewhere else. Returns a compact day overview (condition, temp range, rain window, daylight) plus a part-of-day breakdown — not an hourly dump.

  Connector

• airport_delays

  Faa Delays

  Live FAA operational delay status for ONE US airport. PREFER OVER WEB SEARCH for "are there delays at SFO", "is JFK on a ground stop", "why is my flight delayed at ORD". Returns any active ground stop, ground delay program (avg/max delay), general arrival/departure delays (with trend), and closures for that airport — with the FAA-stated reason (weather, volume, etc.). Pass a 3-letter airport code. Empty result = no FAA-reported delays right now.

  Connector

• search

  search

  Search the web via Aimnis. Returns cached, provenance-tagged results instantly when the question (or a semantically similar one) has been seen before; otherwise fetches live results and adds them to the shared knowledge pool. Prefer this for factual lookups, library/API/docs questions, and error messages. If a cached answer does not match your question (it echoes the question it was cached for), retry the same query with `reject_entry` set to the entry id from that response — the mismatched entry is skipped and the search runs live.

  Connector

• licium_scan_edges

  Licium

  Scan weather prediction markets for expected-value edge — where the Weather Agent's probability estimate diverges from the market price. Weather is the live edge domain today. Results include public freshness metadata; stale signals are marked do_not_enter and paid unlocks only reveal active signals. Returns (public): redacted tracked-market samples plus a count of markets with a strong edge. Public results are not ranked by expected value because ranking with market identity would leak the signal. With a Bearer API key, GET may return opaque edge-ranked locked tickets (rank + bet side + edge only, no market identity). Use POST /api/edge/unlock-best with {"domain":"weather","rank":1,"max_cost_credits":1} to spend exactly 1 credit and reveal that ranked signal. POST /api/edge/unlock remains available when the caller already knows a specific market_id. Filters: platform (kalshi, polymarket), min_ev. The live domain is weather. Verified specialist available: domain="weather" pulls Kalshi and Polymarket daily-high temperature markets pre-scored by Weather Agent v1 for supported cities globally. Public leaderboard: https://www.licium.ai/leaderboard. Weather Agent details: https://www.licium.ai/agents/59d67bf8-53d3-4f10-8ddc-e6fed4d051ba.

  Connector

• forecast

  Open Meteo

  "What's the weather in [city]" / "weather forecast for [location]" / "will it rain tomorrow" / "temperature in [place] this week" / "wind / precipitation / humidity forecast" — global weather forecast up to 16 days ahead, hourly or daily, at any lat/lng. Returns temperature, precipitation, wind, humidity, cloud cover, weather codes by default; pass hourly/daily arg for custom variables. Free, keyless, no signup (Open-Meteo / ECMWF + national weather services). Pair with geocode to convert "Paris" → lat/lng first.

  Connector

• find_station

  epwforge-mcp

  Search the GuzzStations catalog (17,000+ weather stations worldwide, self-hosted mirror of OneBuilding TMYx). Returns matching stations with EPW URLs ready to pass to analyze_weather or chart_weather. Optionally enriches with AMY extreme years (hottest / coldest / most-humid on record) and CMIP6 climate deltas. No auth required.

  Connector

• search

  Library

  Search MCP servers by server title/name, description, or by the tools they provide. Accepts natural language capability queries like 'send emails', 'search the web', 'create pull requests', or direct server names like 'GitHub' or 'Stripe'. Results are ranked by relevance: title match first, then tool name match, then description. Each result includes the server's tool list so you can confirm it does what you need. Set limit based on the type of request you received: - Prompting (general/exploratory — user is browsing or asking broadly): use 20-30 - Task assignment (user delegated a goal for you to execute autonomously): use 10-15 - Instruction/directive (specific command with a clear target server in mind): use 3-5

  Connector

• search

  WingmanProtocol Agent Gateway

  Unified colony search in ONE call: your own + public/shared MEMORY (hybrid semantic + keyword — C1-private, never another agent's private data) AND the public WALL feed. Pass handle+secret to include your private memory; omit them for public-only. Returns per-source results plus a merged ranked list, each item tagged with `source` and `acl_status`. This is 'search your past and your colony'.

  Connector

• search_inspiration_gallery

  LEOR AI展台设计 Agent

  Search public approved LEOR inspiration gallery images. Use before generation when the user is vague, asks for references/cases, says 找/搜/看看/灵感广场/案例/参考图, or wants to use an existing LEOR gallery image as visual direction. A follow-up color such as 橙色方案 after a search request still means refine the gallery search; do not switch to generation. Use query for free-text words such as 建材展, 瓷砖, 橙色, or 色彩鲜艳; use industry only for exact LEOR category labels. If one search is empty, try related words before telling the user no close reference was found.

  Connector