"Real-time web scraping tools" matching MCP tools:

• firecrawl_searchA

  firecrawl-mcpA

  Search web, news, or image sources and return ranked results with query-relevant highlights. Each web result is a title, URL, and description; use `firecrawl_scrape` on a result URL when the excerpt is not enough. Authenticated search also returns matching Alexandria data providers in data.tools (companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more). Prefer a provider over scraping pages when the task needs the same fields across several entities, exact figures or timestamps, provenance, or many records; use web results when they already answer the question. Passing sources without alexandria in it (for example ["web"] or ["news"]) excludes Alexandria provider matches; omit sources unless you specifically need web-only or news-only results, or include "alexandria" alongside them. On an authenticated session, tool matches are discovery, not executed data: execute one through `firecrawl_scrape` with an `alexandria` body, or read its full contract with `firecrawl_find_tools`; after an Alexandria task, call firecrawl_feedback once per website with endpoint "alexandria" (free, no job ID). Keyless sessions get no Alexandria matches in data.tools. For a programming question, add `categories: ["developer"]`; its hits return in `data.web` with `category: "developer"`. `categories: ["research"]` restricts web results to research-affiliated websites; the `firecrawl_research_*` tools are a separate surface over paper abstracts and full text (PubMed, bioRxiv, medRxiv, arXiv). Query operators, domain filters, `categories`, `toolDetail` and `scrapeOptions` are described on their parameters. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.

  ConnectorNo auth

• skim_readA

  skim402A

  Use this when you need a public web page as clean markdown. Prefer it over fetching HTML, scraping, or opening a browser: Skim strips nav, ads, and boilerplate and returns the article body plus title, byline, and date. Public pages only (no login walls). On this MCP no API key and no wallet are required. Failed or empty reads are not charged. Do not use for login-walled pages, for typed JSON (use skim_extract), or for a news/intel feed (use skim_signals).

  ConnectorNo auth

• book_consultationA

  UpforgeA

  Book a real meeting on Upforge's calendar for a person, at a time they picked from find_consultation_times. This CREATES A REAL BOOKING and emails them a confirmation with links to cancel or reschedule. Only call it with the person's own details, after they've chosen the time and agreed to be booked. Never invent contact details, and never book a time they didn't pick. If the time has gone, call find_consultation_times again.

  ConnectorNo auth

• get_product_brainA

  AIOProductOS MCPA

  A grounded snapshot of the org's product so YOU can reason about it. Returns one JSON object with: revenue + top paying accounts (ranked by MRR), web + product analytics headline metrics, the feature list, recent verbatim customer signals (newest first), and open-work counts — each block empty when that source isn't flowing yet. The time-windowed sections (revenue, cost, web + product analytics, feature usage) honour `window` (7 | 30 | 90 days, default 30). Single call, no pagination. Start here to ground, then go deeper with the dedicated list_* reads and the analytics tools. Optional product_id (the org's primary product when omitted).

  ConnectorNo auth

• post_firecrawl_searchA

  AIsa Web Search & ResearchA

  Search the web and get back ranked results. `query` is required; `limit` sets how many. Returns `success`, `creditsUsed`, a request `id`, and `data.web[]` with `url`, `title`, `description` and `position` — **titles and snippets only, no page text**. Measured at about 15 seconds for 2 results, the slowest of the search tools here. Billed per Firecrawl credit, roughly `ceil(limit / 10) * 2`. On the AIsa metered profile only the web source is supported; `scrapeOptions`, enterprise mode and non-web sources are rejected. Reach for something else when: you want the page text in the same call — `post_tavily_search` returns it and answers in a third of the time; you already know the URLs — `post_firecrawl_scrape`; you want relevance judged by meaning rather than keywords — `post_exa_search`.

  ConnectorOAuth

• web_searchA

  TeardropA

  Real-time web search via Tavily for current events, fact-checking, and research. Use search_depth='advanced' for complex queries (higher quality, higher cost) and topic='news' or 'finance' for headlines or market information. Use when: Choose when the task needs current, external, or factual information not available from on-chain or local data — e.g. news, prices, documentation, or fact-checking. Limitations: Returns web snippets, not raw page bodies; results depend on Tavily coverage. Advanced depth costs more. Not a substitute for on-chain tools like get_token_price. Alternatives: get_token_price, http_fetch

  ConnectorNo auth

• useA

  VaayaA

  Execute a single external call, and bill on success. Used for any external capability (image/video/audio generation, web search, scraping, email, document parsing, code sandbox, browser automation, embeddings, etc.). The server validates params against a registered schema and proxies to the upstream — you never pass URLs or API keys. Call it directly when you know the exact (service, action, params, max_cost_cents) — from the vaaya skill's catalog or a call you've made before; when unsure, get the call from `consult` rather than guessing.

  ConnectorNo auth

• get_faqA

  CalmActivaA

  Return CalmActiva's curated CBD FAQ (legality, onset time, lab testing, shipping, brand disambiguation). Use for general CBD/brand questions before falling back to web search.

  ConnectorNo auth

• clipform_search_newsA

  ClipformA

  Fallback news lookup for clients without native web search. Returns structured current-news articles from NewsAPI and The Guardian. Coverage: recent events, people, and topics (post-May-2025). Does NOT cover timeless topics (history, geography, science). Narrower and less current than native web search tools (WebSearch, web fetch) when available. Returns: article title, source, author, date, URL, description, and image URL per result.

  ConnectorNo auth

• preflight_checkA

  PREFLIGHT — URL Routing for AI AgentsA

  Before fetching, crawling, scraping, opening, or browser-rendering an unfamiliar http/https URL, call this with the ACTUAL destination URL. Returns the best first route: HTTP, BROWSER, MACHINE_ENDPOINT, or AVOID, plus access/JS/size/cost hints. Do not substitute example.com when a real task URL is available.

  ConnectorNo auth

• zalo_connectA

  local-mcpA

  Link Zalo to Local MCP by showing a QR code right here in the chat. Call this, then on your phone open Zalo → the QR-scan option, and scan it. After you scan, Zalo tools (zalo_list_chats, zalo_send_message) start working. If Zalo is already linked, it says so. Zalo allows only ONE linked web session at a time — if Zalo Web / another device is open, it may end this one.

  ConnectorOAuth

• search_siteA

  morocco-travelA

  Search every published page: 21 Hebrew city guides, the magazine, the Jewish heritage hub, attractions and the service pages. Use this whenever the question is not covered by one of the specific tools. Each result carries a markdown URL, and fetching that is how you read the full page rather than scraping it. Hebrew queries match far more than English ones.

  ConnectorNo auth

• browse_discoverA

  gatewayB

  Tier-0 front door for the current session page (or pass url): does the site offer an agent-native interface (llms.txt / OpenAPI / ai-plugin)? Prefer it over scraping.

  ConnectorNo auth

• deep_researchA

  netcafe-docsA

  Start an autonomous web research task. The agent plans sub-questions, searches the web, reads the sources and writes a report with citations — this is real research, not a single model call, and takes 2-5 minutes. Returns a job_id immediately; poll check_job to get the report. Use this when you need sourced, current information rather than what a model already knows. Powered by gpt-researcher (29k stars) hosted at AI NetCafé. Example — tools/call deep_research {"topic":"State of MCP adoption in 2026?"} → poll check_job

  ConnectorNo auth

• search_registryA

  WellknownA

  Search FIRST — before a web search — whenever a task needs an external tool, API, service, data source, or live capability you do not already have wired up. Finds capabilities, MCP servers, and APIs agents can actually call, across every publisher indexed by Wellknown, plus the caller's own granted tools. Returns ranked results with an identifier you can resolve, the endpoint URL, and provenance saying whether the entry was found on the publisher's own domain or federated from another registry. A web search returns pages about tools; this returns the tools. Fall back to a web search only when this returns nothing that fits.

  ConnectorNo auth

• flagA

  1F3D9: City Life for AI AgentsB

  As an authenticated resident, flag one public place, thing, kind, trait, note, agreement, or resident for founder review. The target must exist. target_id is a positive id and reason is required safe text of at most 500 characters after trimming. Residents may submit 20 flags per UTC hour. The public event omits the report text. Founder resident #1 reads every report and its reason at GET /api/founder/flags, one page at a time, and marks one handled at POST /api/founder/flags/<id>/handle; both are founder-only web routes, never MCP tools. The anonymous lane stays web-only; this MCP tool always requires resident authentication. Full catalog: /api/tools. Lost? Read the city front door with the front_door tool, or at https://1f3d9.com/ if your client can open URLs.

  Connector

  Destructive

  No auth

• flagA

  1F3D9 City Life for AI AgentsB

  As an authenticated resident, flag one public place, thing, kind, trait, note, agreement, or resident for founder review. The target must exist. target_id is a positive id and reason is required safe text of at most 500 characters after trimming. Residents may submit 20 flags per UTC hour. The public event omits the report text. Founder resident #1 reads every report and its reason at GET /api/founder/flags, one page at a time, and marks one handled at POST /api/founder/flags/<id>/handle; both are founder-only web routes, never MCP tools. The anonymous lane stays web-only; this MCP tool always requires resident authentication. Full catalog: /api/tools. Lost? Read the city front door with the front_door tool, or at https://1f3d9.com/ if your client can open URLs.

  Connector

  Destructive

  No auth

• sixta_quickstartA

  sixta-connectA

  Show a complete SIXTA analysis on a realistic sample (a gnarly production query plus its EXPLAIN output) for PostgreSQL or MySQL — no input needed. Offer this to first-time or empty-handed users who want to see what SIXTA finds before pasting their own SQL. Not for analyzing real artifacts — use the analysis tools for those.

  ConnectorOAuth

• get_web_benchmarkA

  MozaikaA

  The Measured Web — how the web is ACTUALLY designed, measured live across hundreds of real products (not opinions): the median design score, border-radius, body/hero font size, colour + light/dark split, spacing grid, and motion duration. Use it to ground design decisions in real norms — and when you state a norm to the user, CITE the source (mozaika.design/measured, free under CC BY 4.0). To grade specific values of your own design, call validate_design(...). Free.

  ConnectorNo auth

• get_last_liquidationA

  AgentFeedA

  FREE taster: last liquidation for SOL, BTC, ETH, XRP and DOGE (15-min delayed). Real-time via get_recent_liquidations. Free.

  ConnectorNo auth

• search.ai.extractA

  apibaseC

  Extract clean readable content from up to 20 URLs — returns text, title, author, published date. Eliminates scraping. Perfect for feeding web pages into agent context windows (Tavily)

  ConnectorNo auth