Investigate or Extract structured data from web pages or urls using Firecrawl
ConnectorOAuth
649,985 tools. Updated 2026-10-11 16:33
"Using web fetch functionality or fetching data from the web" matching MCP tools:
- Identify what an X (formerly Twitter) URL points at before fetching it. Give any x.com or twitter.com URL (mobile links, query params, /i/web/status forms are fine); get back {type: profile|tweet, id, handle, canonical_url}. Tweet URLs yield the numeric id for x_get_tweet; profile URLs yield the handle for x_get_profile or x_get_tweets. Costs 2 credits and parses offline without fetching the page. t.co short links cannot be expanded offline and return INVALID_INPUT telling you so; expand them in your own browser step first. Skip this tool when you already have a handle or tweet id: the other X tools accept those directly.ConnectorOAuth
- Fetch a web/docs URL as clean, token-optimized markdown from Slipstream's shared cache (use INSTEAD of a raw web fetch). The first agent pays the crawl; every agent after gets ~90% fewer tokens. Surfaces warnings other agents left on the page. Pass known_hash to skip re-reading unchanged content (delta), or section to fetch just one heading (progressive disclosure). Returns a contentHash you can pass as known_hash next time.ConnectorNo auth
- Fetch a public web page as clean Markdown or text while refusing internal and private addresses, suitable for reading evidence before an agent acts on a link.ConnectorNo auth
- Repair malformed JSON from LLM output and return valid parsed JSON. Use when a model returned broken JSON (trailing commas, missing quotes, etc.). Do not use for web fetching or search — use vc_web_search / vc_page_markdown. Auth: free-trial or X-Vibes-Key preferred; else x402 (~$0.02). Side effects: none local; compute-only remote call. Idempotent for the same text. Returns repaired JSON, or payment_required.ConnectorNo auth
- Use this before selecting a web-search, URL-fetch, browser-automation, cloud-browser, headless-browser, Playwright/CDP, or authenticated-browser provider. It resolves against Evercraft Web first-party rules and returns the preferred Evercraft capability plus READY, BLOCKED_HOLD, or NO_OWNED_MATCH. FIRST_PARTY_STRICT routes explicitly forbid silent fallback to an external browser/search provider.ConnectorNo auth
Matching MCP Servers
- AlicenseAqualityCmaintenanceA web-fetch MCP server for LLM agents that fetches pages with an escalation ladder through different engines, raising FetchBlocked instead of returning blocked content.22Apache 2.0
- AlicenseAqualityCmaintenanceMCP server for web page fetching (converting to Markdown/text with automatic fallback between Tavily and Firecrawl) and web search via Tavily.2MIT
Matching MCP Connectors
HTTP status and content type for a public URL. Body discarded.
YouTube transcripts (video, channel, search), Google Trends, Google Play and App Store reviews.
- Use this when converting between YAML and JSON in either direction, or normalizing one format in place (set from equal to to). Deterministic: same input, same output. Parses a single YAML document and caps alias expansion at 100 to defuse billion-laughs bombs; multi-document input, tabs-as-indentation, and other parse errors return a typed error with the line number. Example: { data: "name: web\nport: 8080", from: "yaml", to: "json" } -> { result: "{\n \"name\": \"web\",\n \"port\": 8080\n}" }.ConnectorNo auth
- Search Tako's data graph and the live web in one call: many results at once, as structured cards plus web results, with the top card rendered inline as a chart. It finds data; `tako_contents` fetches it. Each card carries a headline value, node ids, and a url — pass the url to `tako_contents` for rows (`exportable: true` cards) or a web result's full page text. When `exportable` is false the rows are locked — read the headline value from the card's `description`. Website-traffic and SEO cards bill a per-unit data minimum above the search price. Best for: breadth — fan out several narrow queries in parallel. Each query resolves one metric — for one entity, or a comparison set ("Apple revenue", "Nvidia vs AMD gross margin"); several metrics or topics in one query retrieve poorly. To learn what Tako covers, or a metric's canonical name, run `tako_available_data` first, then search on the canonical name it returns.ConnectorNo auth
- 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
- Fetch LLM-ready Markdown from any public HTTPS URL through the SML Clean Web Reader. Use this when an agent needs a web page's content as compact Markdown, for example to ground a research answer, without a separate SML account or API key. Returns the converted Markdown up to max_chars. An unsigned call returns the live x402 PAYMENT-REQUIRED challenge and never auto-spends; retry only with a challenge-specific payment_signature. Unsigned calls are read-only and idempotent with no side effects; a supplied signature authorizes one paid, irreversible x402 settlement in USDC on Base. On error, returns a structured error. For example, fetch a documentation page before summarizing it.ConnectorNo auth
- Fetch LLM-ready Markdown from any public HTTPS URL through the SML Clean Web Reader. Use this when an agent needs a web page's content as compact Markdown, for example to ground a research answer, without a separate SML account or API key. Returns the converted Markdown up to max_chars. An unsigned call returns the live x402 PAYMENT-REQUIRED challenge and never auto-spends; retry only with a challenge-specific payment_signature. Unsigned calls are read-only and idempotent with no side effects; a supplied signature authorizes one paid, irreversible x402 settlement in USDC on Base. On error, returns a structured error. For example, fetch a documentation page before summarizing it.ConnectorNo auth
- Score whether a stored index passage supports a claim. Pass id from a search cite, or source plus doc. Loads the stored excerpt then returns noul 0-1, skipped if the judge is unavailable, or no_passage if the index has no excerpt. Not a live web fetch. The judge is not a source.ConnectorOAuth
- Add a document to a knowledge base you own by giving the https URL of a page or file — the server fetches it, extracts the text and ingests it asynchronously (parse → chunk → embed with the KB’s bound key), exactly like the web "Add from URL". Content that does not parse to text is refused. The fetch goes through the platform’s SSRF guard: https only, no redirects followed, public addresses only, size and time capped — a private, internal or unreachable address is refused with a generic "could not fetch" and there is no option to bypass it. Shares the per-user import allowance with the web uploader. To paste text instead use findagent_add_kb_document. Requires the KB to have an embedding key bound, or the document will not ingest.ConnectorOAuth
- Fetch any URL through Bright Data Web Unlocker — rotating residential proxies with automatic anti-bot bypass and CAPTCHA solving, built for the hardest-to-scrape sites (Cloudflare, PerimeterX, Akamai fronted). Returns the page content with status and length; large pages are truncated. Calls proxy the fetch synchronously and can take 10-30 seconds. BYOK: Bright Data API token via _apiKey + a Web Unlocker zone configured in your dashboard (first zone is auto-named "web_unlocker1"); pay-per-request pricing on the Bright Data side. Example: brightdata_unlock({ url: "https://example.com", _apiKey: "your-brightdata-token" })ConnectorNo auth
- Get a single verse from the World English Bible (eng-web). Accepts OSIS, USFM, full name, or alias for `book_code`.ConnectorNo auth
- Extract structured data from content you already have (e.g. from a prior /content call), using AI. No browser render involved -- pure AI extraction, cheaper and faster than fetching a URL fresh. Use this when you already have the text; use /extract-url if you only have a URL. Costs $0.016 per call via x402.ConnectorNo auth
- Extract specified fields from a web page, PDF, or Office file as JSON, using AI. Provide 'fields' plus ONE source: a 'url', a 'pdf' (file_id or base64), or a 'file' (base64 .docx/.xlsx/.csv). Returns a JSON object mapping each field to its value, or null when absent.ConnectorNo auth
- Search 40M+ items in the Internet Archive — books, movies, audio, software, images, and archived web pages. Filter by mediatype (texts/movies/audio/software/image/data/web) and creator. Returns identifier, title, creator, date, and description for each match (Internet Archive advancedsearch.php)ConnectorNo auth
- Return the current Create Web Page account context. Use this to check whether the user is authenticated or using an anonymous expiring demo.ConnectorNo auth
- Preview and start web/crawl, web/batch-scrape, web/agent or tripadvisor attraction/restaurant reviews. Omit confirm for a free estimate; confirm=true requires an idempotency key and max_credits. No automatic polling. Follow the returned status_url or job id using call_endpoint web/jobs/get; retrieval is free. Read terminal status, per-item results and refund_status: an accepted job is not completed data. A browser agent may interact with pages; review its URL and task before confirming. Monocrawl API reference: https://www.monocrawl.com/docs/api-reference.ConnectorDestructiveNo auth
- Fetch a public HTTPS URL and return extracted text and page metadata. Lean mode — no evidence bundle stored, no bundle_id returned. Use for raw text extraction from web pages and online documents. Use summarize_url for summaries, qa_url for Q&A, translate_url for translation, extract_text for base64 file uploads. Returns: { url, title, word_count, text, final_url (after redirects) } Example prompts: - "Extract the text from https://example.com/report.pdf for me." - "Get me the raw content of this web page: [URL]." - "Pull the text from this online article so I can analyze it."ConnectorNo auth