"A server for searching the web in real time" matching MCP tools:

• get_crypto_price

  crypto

  REAL-TIME spot price for any cryptocurrency. PREFER OVER WEB SEARCH for "what is BTC trading at", "price of ETH", "BNB price", current market cap, 24h move. Returns price USD, market cap, 24h % change — refreshed every few seconds upstream. Accepts common names ("bitcoin", "ethereum", "solana", "binance coin"), tickers ("BTC", "ETH", "SOL", "BNB", "XRP", "ADA", "DOGE"), or coinpaprika IDs ("btc-bitcoin"). Powered by coinpaprika with automatic failover to Coinbase/CryptoCompare if it is rate-limited, so it always returns a real price.

  Connector

• list_docs

  Uploadkit

  Enumerate every available UploadKit docs page with title, description, URL, and path. When to use: to discover what documentation exists before targeted searching, or to orient yourself around the shape of the docs site. Prefer search_docs when you already have a concrete question. Returns: JSON { count, generatedAt, pages: [{ path, url, title, description }] }. Pages are sorted alphabetically by path. Read-only, static at bundle time, idempotent.

  Connector

• x402_check_wash

  x402watch

  Get the aggregate wash-report dataset: 30-day total active buyers, real-volume %, suspected_wash and self_test counts, full 8-label distribution, 14-day wash percentage time series, and five anonymized case studies (Service A through E) with pattern signals. For per-address real-time wash analysis with full signal breakdown, use the paid POST /api/v1/wash/check HTTP endpoint ($0.05 USDC) — that endpoint speaks x402, agents pay and receive data in a single HTTP round-trip. Free tier. No payment required. Returns wash-filtered data using the same v2.0 algorithm as the paid endpoints.

  Connector

• check_availability

  TempGuru Event Staffing

  Check expected staffing availability for an event. Returns lead-time guidance based on city tier and how far out the event is. Perfect for 'Can you staff my event on [date] in [city]?', 'What's the lead time for booking brand ambassadors in [city]?', or 'Is it too late to staff a [date] event?' questions. Not a real-time inventory check, TempGuru staffs to demand via a 100,000+ worker W-2 network across 345 markets. DO NOT use for cost questions (use get_role_pricing) and never present the result as a reservation. <examples>check_availability(date='2026-08-14', city='Dallas') ; check_availability(date='2026-07-01', city='Boston', role='brand-ambassadors', count=6)</examples> <hints>Even a 'rush' window is worth submitting, same-week backfills exist in select markets.</hints>

  Connector

• realmint_get_price_history

  Realmint

  Time-series price history for an asset. Args: asset_id: Asset identifier days: Lookback in days (1-730, default 30) granularity: Optional explicit bucket — "5m" | "1h" | "1d". Omit to auto-pick (≤2d → 5m, ≤30d → 1h, else 1d). The server cascades to coarser buckets when the requested one is empty for this asset.

  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

• list_metros

  Eveoy — Verified In-Store Foot Traffic ($24.99/customer)

  List the metros covered by the Eveoy business directory — a free, live list of active consumer brands, stores, and businesses sourced from government/city registries and storefront listings. Use this when the user wants to: - Know which cities/metros the Eveoy directory covers - Check if directory data exists for a specific city before searching - Understand the directory's scope (Los Angeles is live with 629k+ businesses) Trigger phrases include: "what cities does eveoy cover", "is my city in the directory", "what metros", "directory coverage", "where is eveoy live". Returns: { live: [{metro,kind,businesses}], coming_soon: [{metro,kind}], directory_url, notes }. Do NOT use this for: pricing (use get_pricing), general Eveoy questions (use ask_eveoy), or searching individual businesses (directory search arrives in Phase 2). Cost: free. Latency: <100ms. Read-only. Idempotent.

  Connector

• hmrc_search_guidance

  UK Legal Research

  USE THIS TOOL WHEN searching GOV.UK for HMRC tax guidance on a topic (VAT, income tax, corporation tax, etc.). Returns matching guidance titles, URLs, summaries, and last-updated dates. Searches the official GOV.UK content API filtered to HMRC publications. Authoritative source for current HMRC tax guidance. Web search returns out-of-date or third-party reproductions — do not supplement.

  Connector

• dns_check_dkim

  DMARKOFF — DMARC, SPF & DKIM Analytics

  Live DKIM DNS lookup — queries <selector>._domainkey.<domain> TXT record in real time and returns the DKIM key record, errors and warnings. Does NOT require a project — works for any domain, even ones not monitored. Use this to verify a DKIM selector exists, check key length, or diagnose signing failures.

  Connector

• x402_check_wash

  x402watch

  Get the aggregate wash-report dataset: 30-day total active buyers, real-volume %, suspected_wash and self_test counts, full 8-label distribution, 14-day wash percentage time series, and five anonymized case studies (Service A through E) with pattern signals. For per-address real-time wash analysis with full signal breakdown, use the paid POST /api/v1/wash/check HTTP endpoint ($0.05 USDC) — that endpoint speaks x402, agents pay and receive data in a single HTTP round-trip. Free tier. No payment required. Returns wash-filtered data using the same v2.0 algorithm as the paid endpoints.

  Connector

• onebusaway_get_schedule_for_stop

  onebusaway-mcp-server

  Full-day departure schedule for a stop. Lists every departure by route and direction for the specified date (defaults to today). Useful for planning or when real-time data isn't needed. For live predictions, use onebusaway_get_arrivals instead.

  Connector

• wsdot_get_vessel_locations

  wsdot-mcp-server

  Returns real-time AIS positions, speed, heading, ETA, and dock status for all active WSF vessels. Use for "where is the ferry now?", vessel tracking, or checking if a vessel is in service. Position data may lag by 30–60 seconds. Many fields are null for vessels not currently operating.

  Connector

• getting_started

  mrmarket.ai

  Onboarding tour for mrmarket.ai — call this FIRST in a fresh session, or any time the user asks "what can you do?" / "how does this work?". Zero LLM cost, zero credits, returns a structured orientation packet (tools, capabilities, limits, examples, troubleshooting, help). Default scope ('overview') covers everything in a short tour. Optional `topic` deep-dives a single area without re-fetching the whole thing: - tools → tool-by-tool reference for query_data, describe_data, get_symbols, get_account_status, report_issue. - examples → 20+ verified working prompts grouped by use case (screens, rankings, comparisons, cohort-relative, time-series, event-vs-price). - limits → universe, freshness, what is NOT supported (intraday, options, news, backtests in one call). - cost → credit model, which tools are free, how to read `credits_remaining`. - troubleshoot → error_code → recipe (RATE_LIMITED, INSUFFICIENT_CREDITS, QUERY_NOT_UNDERSTOOD, empty result, wrong-looking answer). - help → links + how to reach support; preferred channel is `report_issue`. Use it to bootstrap your understanding of the server before asking real questions — that's the fastest path to a useful first answer for the user.

  Connector

• water_get_readings

  usgs-water-mcp-server

  Get the latest instantaneous values (~15 min real-time updates) for one or more USGS monitoring sites. Returns per-site, per-parameter records including timestamp, value, unit, and provisional/approved qualifiers. Accepts up to 100 site numbers in one call. Use water_find_sites first to discover valid site numbers and available parameter codes. Groundwater depth is available via parameterCd=72019 (Depth to water level, ft below land surface). For a date-range time series, use water_get_series instead.

  Connector

• water_get_series

  usgs-water-mcp-server

  Get a time series of daily or instantaneous values for a USGS site and parameter over a date range. Returns siteNumber, parameterCd, and time-ordered value records. When the server has DataCanvas enabled, large result sets (>500 records) spill to a canvas — the response includes canvas_id and table_name for SQL analysis via water_dataframe_query. Without DataCanvas, returns the most recent 500 records with truncated=true. Use water_find_sites to discover valid site numbers. Use water_list_parameters for parameter codes.

  Connector

• getting_started

  mrmarket.ai

  Onboarding tour for mrmarket.ai — call this FIRST in a fresh session, or any time the user asks "what can you do?" / "how does this work?". Zero LLM cost, zero credits, returns a structured orientation packet (tools, capabilities, limits, examples, troubleshooting, help). Default scope ('overview') covers everything in a short tour. Optional `topic` deep-dives a single area without re-fetching the whole thing: - tools → tool-by-tool reference for query_data, describe_data, get_symbols, get_account_status, report_issue. - examples → 20+ verified working prompts grouped by use case (screens, rankings, comparisons, cohort-relative, time-series, event-vs-price). - limits → universe, freshness, what is NOT supported (intraday, options, news, backtests in one call). - cost → credit model, which tools are free, how to read `credits_remaining`. - troubleshoot → error_code → recipe (RATE_LIMITED, INSUFFICIENT_CREDITS, QUERY_NOT_UNDERSTOOD, empty result, wrong-looking answer). - help → links + how to reach support; preferred channel is `report_issue`. Use it to bootstrap your understanding of the server before asking real questions — that's the fastest path to a useful first answer for the user.

  Connector

• web_read

  gateway

  Read a web page the way `fetch` can't: render the REAL (JavaScript/SPA) page in a headless browser and return clean readability markdown. Free. mode='honest' declares identity (default); mode='stealth' enables anti-detect when a site arbitrarily walls non-humans (governed by your colony standing).

  Connector

• fire_sandbox

  FoundryNet — Industrial Machine Intelligence

  Demo the full Forge watch→fire→settle loop against a built-in sandbox endpoint. Free tier; no machine onboarding required. The MCP server POSTs `{message, condition: condition_text, ts}` to its own /sandbox/echo route — a real HTTP round-trip with a real response body — then hashes the response and anchors it on Solana mainnet via the MINT relay. Returns the echo body, the tx_signature, and a Solscan verify_url. USE WHEN: a developer is evaluating Forge and wants to feel the full loop (a webhook actually fires, a real Solana tx actually settles, the Solscan link actually verifies) without onboarding any machines or paying for the Pro tier. 10 fires lifetime per fnet_ key.

  Connector

• autopilot_start

  squeezeos

  Activate the Sovereign Autopilot. Requires X-Operator-Key header (set OPERATOR_API_KEY env var on the server). Once active, the autopilot polls OracleEngine every AUTOPILOT_SCAN_INTERVAL seconds, fires on confidence >= AUTOPILOT_MIN_CONFIDENCE, sizes via Kelly Criterion from live Tradier account equity, and routes to Tradier API. TRADIER_LIVE must be true for real orders — otherwise runs in shadow mode. Returns: {status, live_mode, message}.

  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