811,251 tools. Updated 2026-11-20 10:28
"How to describe web content using a URL" matching MCP tools:
- Fetches a public web page and returns its content as clean Markdown. WHEN TO USE: you need to read a page — documentation, an article, a product page — to answer, summarize or quote it; or the user wants a page as Markdown. HOW IT WORKS: - url: a public http(s) address. Private networks, localhost and addresses with credentials are refused. - Reads the HTML the server sends (like a simple browser, without running JavaScript). Pages that build their content with JavaScript have no text to convert — the error says so. - onlyMainContent (default true) drops menus, headers, footers, sidebars, cookie banners and ads. Set false to keep the whole page. - pages above 1 also follows links on the same site (same folder and below), breadth-first, up to that many pages (max 20), respecting robots.txt. Slower: a few seconds per page. - Limits per page: 15 seconds and 5 MB. PDFs and non-HTML files are not converted. RETURNS: for each page, its Markdown with absolute links and images, plus title, description and language when the page has them; pages that failed are listed with the reason. link: this tool's web page with the same request. ERRORS say why the page could not be read and whether retrying makes sense.ConnectorNo auth
- 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
- Render a PDF drawing's vector content to a PNG you can look at. Images, shadings, and transparency are not drawn — they are reported by describe_pdf — so this shows line work and text, not a page facsimile. For a DXF use render_dxf; if you do not know the format, use render_doc. Renders the first page/sheet by default; pass `space` (a name from a describe reply's `spaces`) to render another one. Some chat UIs do not display the returned image to the user: for URL sources the result also includes a direct image link — show it (e.g. as a markdown image) when they need to see the render. When the user wants to see or explore the drawing themselves, prefer view_dxf (interactive viewer) — if your platform gates it behind user approval, offer it and ask rather than substituting a static render.ConnectorNo auth
- Search the TCLP knowledge graph using fusion search (semantic + BM25). Args: query: Free-text search query (max 1000 characters). node_type: Content scope — "tclp" (clauses, glossary terms, guides) or "all". Laws, regulations, standards and frameworks are not searchable here: use `find_legal_resources`. content_type: Return only one content type: "clause", "glossary_term" or "guide". Omit to search every type. limit: Maximum number of results to return (1–50). rerank: Whether to apply RRF reranking when combining graph and text results. include_full_text: Include each hit's full body text (Markdown). Off by default — bodies are large; request only when you need the content, and prefer a small `limit` when you do. Returns: JSON with "meta" (totals, timing) and "results" (ranked hits with title, url, content_type, scores, summary, optionally relationships_text, related and full_text). `summary` is short plain text: the clause summary, the first paragraph of a glossary definition, or a guide's excerpt. It is null when the item has none. `child_name` is a clause's child name (e.g. "Odhran's Clause"), null for other content and for a clause that has none; text search also matches it. Each hit's "references" lists the instruments it cites: pass a reference's `work_id` to `get_legal_resource` for details. A reference's `edge` (governs, references, describes) says how the content relates to the instrument; it is not a statement of the instrument's legal effect. An empty list means the hit cites no instruments. null with "lrsf" in meta.degraded means references could not be loaded: do not conclude that the hit cites no instruments.ConnectorNo auth
- Search the TCLP knowledge graph using fusion search (semantic + BM25). Args: query: Free-text search query (max 1000 characters). node_type: Content scope — "tclp" (clauses, glossary terms, guides) or "all". Laws, regulations, standards and frameworks are not searchable here: use `find_legal_resources`. content_type: Return only one content type: "clause", "glossary_term" or "guide". Omit to search every type. limit: Maximum number of results to return (1–50). rerank: Whether to apply RRF reranking when combining graph and text results. include_full_text: Include each hit's full body text (Markdown). Off by default — bodies are large; request only when you need the content, and prefer a small `limit` when you do. Returns: JSON with "meta" (totals, timing) and "results" (ranked hits with title, url, content_type, scores, summary, optionally relationships_text, related and full_text). `summary` is short plain text: the clause summary, the first paragraph of a glossary definition, or a guide's excerpt. It is null when the item has none. `child_name` is a clause's child name (e.g. "Odhran's Clause"), null for other content and for a clause that has none; text search also matches it. Each hit's "references" lists the instruments it cites: pass a reference's `work_id` to `get_legal_resource` for details. A reference's `edge` (governs, references, describes) says how the content relates to the instrument; it is not a statement of the instrument's legal effect. An empty list means the hit cites no instruments. null with "lrsf" in meta.degraded means references could not be loaded: do not conclude that the hit cites no instruments.ConnectorNo auth
- Search Vectree's library of ~95,000 interactive concept diagrams by meaning, not keywords. Vectree explains how things work as zoomable, labelled schematics — each diagram breaks a topic into nodes you can read or drill into. Use this when the user wants a diagram, a visual explanation, a systems overview, or a map of how the parts of something fit together. Describe the topic in natural language; the search is semantic, so a full question works better than a bare keyword. Results are ranked by how closely they match and by the quality of the model that generated them. Each result carries a slug — pass it to `get_diagram` for the full content of one diagram. Only public, already-generated diagrams are searched. Nothing is generated on demand, so a topic with no match simply has no diagram yet.ConnectorNo auth
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server that fetches raw HTML content from a given URL to provide web context to LLMs.1-
- AlicenseAqualityCmaintenanceMCP server that converts web page URLs to Markdown via the Zyla API.160 npmMIT
Matching MCP Connectors
26 tools: web pages to Markdown, metadata, tech stack, SSL, SEO, domains, email auth and SSO checks.
26 tools for AI agents: read any web page as clean Markdown, get metadata, structure and tech stack, and check redirects, SSL, security headers, robots.txt, sitemaps, feeds, WHOIS/DNS, SEO, broken links, email authentication (SPF, DMARC, DKIM) and SSO (SAML, OIDC), plus cron, regex, color, Unicode, time zone utilities and Hyperliquid market data. Hosted on Apify; authenticate with an Apify API token (Bearer). Pay per successful call ($0.001-$0.003).
- Use when the user wants to see a saved project, or you need to describe it: returns a signed URL of the studio's last saved render, valid for an hour, and the PNG inline when include_image_data is true (only on hosts that display image content; elsewhere it costs many tokens for nothing). Nothing to show until the project has been opened and saved once. Do not use for Generate runs; get_generation_preview covers those.ConnectorOAuth
- Scrape any webpage and return its content using Zenrows (Fetch). Returns full-page content (markdown/HTML/PDF/screenshot). For structured JSON fields (products, articles, listings), the extract tool returns parsed fields instead of a full page body. By default the request uses automatic mode (mode=auto): Zenrows adds JS rendering or premium proxies per page only when a plain request does not return the page, and charges only for the configuration that succeeds. Pass just the URL. Set js_render or premium_proxy only to force a fixed configuration. Doing so switches off automatic mode, and every request is billed at that configuration's cost (premium_proxy with js_render is 25x a basic request). Examples: Default: { url: "https://example.com" } Geo: { url: "https://example.com", proxy_country: "US" } Forced: { url: "https://spa.com", js_render: true }ConnectorOAuth
- Register existing pages or third-party URLs as tracked Content Hub items so Athena attributes citations and mentions to them. Creates external content rows from bare URLs with no generation and no credit cost. Tracking starts immediately: the normalized URL becomes the citation/metric join key, so pages cited in the website's monitored AI responses accrue metrics with no publish step (use it for guest posts, partner placements, or any page Athena did not generate). Idempotent per URL: a URL already present on the website (any content type) is not duplicated; the response lists it under skipped with the existing content_id and type. Check that type before chaining destructive calls (a skip can resolve to first-party generated content that shares the URL). Rows are created without page text, which citation tracking does not need; the body can be filled from the app later. Duplicate URLs within one call (including tracking-param variants of the same page) collapse to one row, first occurrence wins. Optional sheet_id files rows under a Content Hub tab; view-type tabs resolve to the main pool (null), echoed per row. Optional per-URL fields set the customer's own Content Hub columns on the created row, addressed by column name as shown on the destination tab (text, number, date, checkbox, link, and multi-select columns; unknown multi-select options are created). An unknown column name or a value that does not fit the column type rejects the whole call and nothing is tracked; skipped URLs keep their existing values. If the user names a destination tab, resolve its id with get_content_hub_sheets before tracking. Omitting sheet_id uses the shared pool, not the user's currently open tab. After the call, report created_count and skipped_count separately, name the returned destination_name, and share content_hub_url so the user can open each item. Skipped rows keep their existing tab: use their returned destination and never describe them as newly added or moved.ConnectorNo auth
- Rename a page (`new_name`) and/or move its URL (`new_slug`). Supply either or both — omitting `new_slug` derives it from the new name. Every internal link across the site is rewritten to the new URL, the navigation is re-synced, and link TEXT naming the old page is updated too, so this is the ONLY safe way to move a page: editing the file's name through update_variation_file leaves every link pointing at a URL that no longer exists. The homepage's URL cannot be changed. The page's content survives the move — its content namespace is deliberately not recomputed. Publish the site for the change to reach visitors; until then the live site keeps the old URL.ConnectorOAuth
- [writes flayr data · `write` scope] Step 1 of attaching a LOCAL file (video, image or audio) to a draft. Returns a single-use, short-lived `uploadUrl`. Step 2: POST the raw file bytes to it with the file's Content-Type, e.g. `curl -X POST -H "Content-Type: video/mp4" --data-binary @clip.mp4 "<uploadUrl>"` — the JSON response has a `storageId`. Step 3: pass it as `videoStorageId` or `imageStorageId`, or collect 2-20 ids into `imageStorageIds` for a carousel on create_content or update_content. get_uploaded_media returns the public URL without a draft. For music-library audio, pass storageId to music_tracks_create instead. For media already on the web, skip this and pass `videoUrl` / `imageUrl` instead. Returns 413 when the account's storage is full. (Wraps POST /api/v2/media/upload-url.)ConnectorOAuth
- Fetch a page now and compare it with the previous snapshot of the same URL, returning whether it changed and a unified diff (no LLM). When to use: monitoring a page for updates - prices, docs, policy pages, SEO titles/meta; first call stores the baseline, later calls return added/removed lines. Do not use: for one-off reading (web_fetch) or structured fields (web_extract_schema). Returns: {ok, url, baseline, changed, diff, added_lines, removed_lines, previous_ts, current_ts, title, hash, chars, fetched_cached, took_ms, _metering}. fresh=true (default) adds a cache-busting query to bypass the 6h page cache; pass fresh=false to compare cached content. Snapshots are kept per URL in SQLite (latest only). Metered: shares the web free bucket (100 calls/day per IP), then 1 credit per call over x402.ConnectorNo auth
- Fetch a page now and compare it with the previous snapshot of the same URL, returning whether it changed and a unified diff (no LLM). When to use: monitoring a page for updates - prices, docs, policy pages, SEO titles/meta; first call stores the baseline, later calls return added/removed lines. Do not use: for one-off reading (web_fetch) or structured fields (web_extract_schema). Returns: {ok, url, baseline, changed, diff, added_lines, removed_lines, previous_ts, current_ts, title, hash, chars, fetched_cached, took_ms, _metering}. fresh=true (default) adds a cache-busting query to bypass the 6h page cache; pass fresh=false to compare cached content. Snapshots are kept per URL in SQLite (latest only). Metered: shares the web free bucket (100 calls/day per IP), then 1 credit per call over x402.ConnectorNo auth
- Upload a JPEG, PNG, GIF, WebP or PDF file sent as base64 content and add it to the media library. WordPress checks the file as for any upload and creates the image sizes; the file is public under its URL afterwards, and each call adds a new file. The base64 text is limited to 8 MB, so the file to about 6 MB (less where the site sets a lower limit). Returns {uploaded: true, id, url}. Needs upload_files, and the right to edit post_id when the file is attached to it. A file already on the web is added with wp_upload_media_from_url. Forwarded by AlphaBridge Connect to the one site this connection reaches.ConnectorDestructiveOAuth
- Fetch a page now and compare it with the previous snapshot of the same URL, returning whether it changed and a unified diff (no LLM). When to use: monitoring a page for updates - prices, docs, policy pages, SEO titles/meta; first call stores the baseline, later calls return added/removed lines. Do not use: for one-off reading (web_fetch) or structured fields (web_extract_schema). Returns: {ok, url, baseline, changed, diff, added_lines, removed_lines, previous_ts, current_ts, title, hash, chars, fetched_cached, took_ms, _metering}. fresh=true (default) adds a cache-busting query to bypass the 6h page cache; pass fresh=false to compare cached content. Snapshots are kept per URL in SQLite (latest only). Metered: shares the web free bucket (100 calls/day per IP), then 1 credit per call over x402.ConnectorNo auth
- Fetch a page now and compare it with the previous snapshot of the same URL, returning whether it changed and a unified diff (no LLM). When to use: monitoring a page for updates - prices, docs, policy pages, SEO titles/meta; first call stores the baseline, later calls return added/removed lines. Do not use: for one-off reading (web_fetch) or structured fields (web_extract_schema). Returns: {ok, url, baseline, changed, diff, added_lines, removed_lines, previous_ts, current_ts, title, hash, chars, fetched_cached, took_ms, _metering}. fresh=true (default) adds a cache-busting query to bypass the 6h page cache; pass fresh=false to compare cached content. Snapshots are kept per URL in SQLite (latest only). Metered: shares the web free bucket (100 calls/day per IP), then 1 credit per call over x402.ConnectorNo auth
- Fetch a web page and return its title and main content as Markdown. Use it to read a specific page in full: a URL the user gave you, or a promising result from web_search whose snippet was not enough. Only http and https URLs are supported. Pages may be served from a shared cache; set refresh to read the live page (billed at the full rate) when the page changes often or the cached copy looks stale.ConnectorNo auth
- Reads one public web page by URL and returns its content as markdown (text, truncated, total_chars). Use it when the URL is known; it does not search (use google_search), and Zillow or eBay URLs are refused free (use search_zillow or search_ebay). Costs 1 credit, 5 with render_js, 10 with premium or challenge_mode, 25 with render_js and premium; blocked or empty pages are not charged. A page not ready within 25 seconds returns a job_id instead; async=true returns one at once. Poll with the same url and job_id; jobs are kept 1 hour. Required: url.ConnectorNo auth
- Identify a named employer before using it as a sourcing filter. Pass the company name and any LinkedIn company URL or website the user supplied or that you verified on the web; never invent URLs. Checks PDL's company directory only, does not search for people, and says nothing about how many candidates exist. A supplied LinkedIn URL stays usable even when the directory cannot match it; source and providerStatus tell these outcomes apart. Pass the returned name and slug to build_sourcing_query, or mention the name and LinkedIn URL in an edit_sourcing_query request. Requires OAuth.ConnectorOAuth
- Request a short-lived presigned PUT URL for uploading publishing content. Use when content exceeds practical inline-parameter limits (~10 KB). After uploading the file to the returned URL with an HTTP PUT, pass the file_id as content_ref to submit_document or create_new_version. The URL expires in 10 minutes and accepts a single file up to 50 MB.ConnectorAPI key
- Scope: none. Return a single voice's preview audio URL so the user (or the agent) can hear how a Gemini Omni voice sounds before using it in a generation. Faster than `list_gemini_omni_voices` when you already know the id (e.g. user said 'play me Kore' or you just picked one from the catalog). ARGS: `voice_id` — one of the 30 known ids (e.g. `kore`, `puck`, `achernar`). Unknown ids return `invalid_voice_id` with a hint to call `list_gemini_omni_voices`. RETURNS: `{ voice: {id, label, gender, description, preview_url}, preview_url, message }`. The `preview_url` is a ~7s mp3 hosted on the Kubeez web app — surface it directly to the user so they can play it. USE WHEN: the user asks 'what does <voice> sound like', 'play that voice', or you want to confirm a pick before passing it to `generate_media`.ConnectorOAuth