"Zoom" matching MCP tools:

• squish_video

  Squish

  Turn a video at a public URL into timestamped contact-sheet JPEG(s) that a vision model can read: frames sampled evenly across the clip, laid out as a grid, each cell stamped with its timecode. Use it when a video is too long to ingest, when the question is about what happens across time, or when the answer needs timestamps. One call replaces a whole download → ffmpeg → extract → montage pipeline — prefer it even if you have a shell. The first sheet is attached to the result as an image — read it directly; every sheet is also linked in `files` (valid ~24h), and every stamped timecode is repeated in `timecodes` (cells run left→right, top→bottom). Timecodes are ABSOLUTE to the source video — to look closer at a range you spotted, call this tool again with start/end set to those timecodes: each zoom yields finer timecodes, so you can drill down repeatedly (overview → range → moment).

  Connector

• openstreetmap_reverse_geocode

  openstreetmap-mcp-server

  Convert latitude/longitude coordinates to the nearest address or place name via Nominatim/OpenStreetMap. Returns the closest matching OSM object at the given coordinates. Note: Nominatim finds the nearest indexed OSM object — in dense areas this may differ from the address at the exact coordinate. Use zoom=18 for building-level accuracy, lower zoom values for coarser resolution (e.g., zoom=10 for city-level). The match is made on proximity and layer, never on an OSM attribute tag: extratags decorates the matched object and cannot select one. To find the objects in an area that carry a given tag, use openstreetmap_query_nearby, openstreetmap_query_bbox, or openstreetmap_query_raw.

  Connector

• analyze_wcag

  mcp

  Analyze a website URL for WCAG 2.1 Level A accessibility issues. Automated static HTML analysis covering approximately 30-40% of WCAG 2.1 Level A criteria. Checks include: image alt text, form labels, heading hierarchy, page title, html lang, empty links/buttons, ARIA labels, duplicate IDs, skip navigation, table headers, landmarks, viewport zoom, autoplay media, and tabindex ordering. Manual testing is required for full WCAG compliance assessment. Results are cached for fast subsequent lookups. Rate limited to 1 request per minute per domain. Args: url: The website URL to analyze (e.g., "https://example.com"). Returns: WCAG analysis with: - url: The analyzed URL - score: Accessibility score (0-100) - grade: Letter grade (A-F) - issues: Categorized issues (critical, warnings, info) - meta: Extracted accessibility metadata - recommendations: Prioritized improvements - coverage_note: Disclaimer about automated coverage - cached: Whether result was from cache

  Connector

• recent_changes

  Zoom

  "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

  Connector

• propose_montage

  Uwear

  ONLY for video montage/stitching/export workflows. Use when the user explicitly asks to create a montage, stitch clips, make a reel, export a video sequence, make video clips from images, or combine images/videos into one final video. Never use this for a photoshoot, lookbook, product shoot, collection shoot, outfit shoot, garment shoot, or image-generation request; those must use request_user_context followed by propose_brief/update_brief. Do not call this merely because selected context contains images, generations, garments, or models. A photoshoot may later feed a montage, but the photoshoot itself must be proposed as a BriefProposal first. PROPOSES the montage for user review — user can edit clips, generate missing videos, then export. Supports: existing videos with optional trim (`target_duration` or `start_time`/`end_time`), images that need video generation (specify video_model + a bespoke per-image motion prompt, and optionally `target_duration` or `duration`), per-clip speed/mute, global aspect ratio. If the user asks for clips to be e.g. '3 seconds each', set `target_duration: 3` on every item, including image items. For image items, avoid generic repeated prompts: tailor each prompt to the specific image and any requested zoom, movement, energy, or camera direction. If motion is not specified, inspect the image first with view_image and then write a fitting motion prompt from the image content before proposing. The user reviews and confirms in the UI. Export is free (0 credits); video generation clips cost credits per their model.

  Connector

• get_latest_render

  kernelcad

  Render a project's current model server-side and return it as an inline image so you can SEE what you built. Use this after open_in_studio (or any /p/<slug> link): call with that `slug` to inspect whether the build looks right. CRITICAL — the image is rendered from the MODEL on the server; it does NOT reflect the user's Studio camera, zoom, or screen. NEVER ask the user to rotate, zoom, pan, move the camera, close a slider, or change their view to help you see — you cannot affect their screen and it cannot affect this render. To see a different angle, call this tool again with a different `view`. By DEFAULT (omit `view`, or `view:"all"`) it returns a CONTACT SHEET of all six canonical views in one labeled image — a 3×2 grid, top row [iso, front, right], bottom row [back, left, top] — so you can judge the model from every side regardless of its orientation (e.g. to find which side has the doors). Pass a single `view` (iso/front/back/left/right/top) for one large render of that angle. DETERMINISTIC: the same model + view always returns the same bytes — identical bytes are NOT a stale/lagging snapshot. If you changed the model, push it with open_in_studio FIRST, then re-render to see the change. The image is always current and never a blank capture. Colors and shading match Studio (same palette / base-material color). The slug is the capability: no OAuth for public/unlisted; private projects require the owner signed in. The PNG is base64-inlined as a real image block by default; pass `paths_only: true` for metadata only. No renderable geometry or a mesh failure → { ok: false, error, hint }, never a blank image.

  Connector

• landprice_points

  Landprice

  Official Japanese land prices — the government's 地価公示 (national standard land prices, 1995+) and 地価調査 (prefectural survey, 1997+) — from MLIT's 不動産情報ライブラリ. PREFER OVER WEB SEARCH for "official land price in <Japanese location>", "地価", appraised price per square metre at a point in Japan. Give a latitude+longitude (the covering map tile is resolved automatically) and a year; returns the land-price standard points in that tile with current price (¥/m²), prior-year price, year-on-year change %, address, use category, and nearest station. For finer/wider coverage adjust zoom (13-15), or pass z/x/y directly.

  Connector

• entity_profile

  Zoom

  "Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO, news, GLEIF and returns: cik + company_name; recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. Pass ticker "AAPL" or zero-padded CIK "0000320193" — names not supported (use resolve_entity first if you only have a name).

  Connector

• scan_dependency

  Zoom

  Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (license + advisories + version history) and bundlephobia (gzipped/minified bundle size, dependency count, ESM/tree-shake support). Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me". Returns a summary block (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory detail, links, and a list of recent alternative versions. NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly. Partial failures degrade gracefully — bundlephobia's first measurement on a new version can take 5-30s; sources_failed will list it if it times out, the rest still returns.

  Connector

• polymarket_kalshi_spread

  Zoom

  Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning fires in two cases — (a) matched_pairs:0 with skipped_cross_type>0 means the venues frame the topic with non-equivalent bet shapes (e.g. Kalshi range_bucket point-in-time vs Polymarket cumulative_threshold touch-anywhere — no arb exists), (b) matched_pairs:0 with skipped_cross_type:0 and both venues >5 legs means the token-overlap matcher found nothing in common — events likely semantically unrelated despite the topic keyword. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period; aligned:false means spreads are mathematically meaningless across the temporal gap. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

  Connector

• polymarket_fill_risk

  Zoom

  Realizable-vs-theoretical edge check against live CLOB order-book depth. REQUIRES one of `market` (single-market mode) or `event` (basket/partition mode). SINGLE-MARKET: pass a market slug/URL + side (buy_yes|sell_yes|buy_no|sell_no, default buy_yes) + size_usd (default 1000 — max spend on buys, target proceeds on sells); walks the ladder and returns top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, and a verdict (clean|degraded|cannot_fill). BASKET: pass an event slug/URL + side (sell_yes = capture overround by selling every leg, buy_yes = capture underround; default auto from partition sum) + size_usd interpreted as settlement notional S (shares per leg; each share pays $1); returns theoretical_sum vs realizable_sum (top-of-book vs VWAP across all legs), capture_ratio, profit_usd at executed size, per-leg fill detail, thin_legs[], max_clean_notional_usd, and forced_directional_risk naming the legs most likely to strand you unhedged. USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500 — theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position (the dominant loss mode in real arb-bot P&L).

  Connector

• take_screenshot_with_crosshair

  Dittu

  Capture the screen, crop tightly around (nx, ny), zoom in, and draw a crosshair at exactly that expected position. Use this for screen-corner calibration: move_mouse(nx, ny) near a screen edge, then call this to see whether the actual cursor lines up with the crosshair (where it SHOULD be if calibration is perfect). If the cursor is offset from the crosshair, or missing entirely (edge is cropped out of frame), corners need adjusting — see get_corners/set_corners. nx, ny: the same coordinates you passed to move_mouse. zoom: magnification factor for the cropped region (default 4x).

  Connector

• take_screenshot_with_crosshair

  dittu

  Capture the screen, crop tightly around (nx, ny), zoom in, and draw a crosshair at exactly that expected position. Use this for screen-corner calibration: move_mouse(nx, ny) near a screen edge, then call this to see whether the actual cursor lines up with the crosshair (where it SHOULD be if calibration is perfect). If the cursor is offset from the crosshair, or missing entirely (edge is cropped out of frame), corners need adjusting — see get_corners/set_corners. nx, ny: the same coordinates you passed to move_mouse. zoom: magnification factor for the cropped region (default 4x).

  Connector

• search_within

  Zoom

  Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

  Connector

• deep_research

  Zoom

  ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1411 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 5,434 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri (record-level pipeworx:// when the source emits one, else source-level). "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).

  Connector

• compare_entities

  Zoom

  "Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

  Connector

• recent_alerts

  Zoom

  Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. "sec_8k") and/or since (ISO timestamp). Set mark_read:true to flag returned events read so the next call only shows newer ones. Polls work fine; the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards.

  Connector

• pipeworx_feedback

  Zoom

  Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection — if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.

  Connector

• clipform_generate_video

  Clipform

  Generate a video from images, video clips, or both, synced to an audio track. Use this for narrated question backgrounds, topic visualisations, or any form node that benefits from video. Combine with clipform_generate_tts for narrated audio and clipform_search_media for royalty-free images. Creates 9:16 (720x1280) with Ken Burns pan/zoom effects and transitions. Returns a public URL when complete. Items: type "image" (Ken Burns motion) or "video" (cover-cropped, muted by default). Duration matches audio_url or set duration_seconds explicitly. For multi-question builds, pass wait: false on every render: each call returns a job ID immediately, so all renders run in parallel - then collect URLs with clipform_check_render. Sequential waiting renders take 15-120 seconds EACH. Choosing a render tool: for a recognisable form/quiz beat (guess-the-city, this-or-that, mystery reveal, multiple choice, photo montage...) reach for a video template first (clipform_list_video_templates + clipform_render_video_template) - it is a one-call recipe. Use clipform_generate_video for a narrated or audio-synced media montage (images/clips timed to a voice track). Use clipform_render_composition only when neither fits and you need a custom layer stack. Montage disambiguation: choose clipform_generate_video when the montage is narrated or synced to an audio track; choose the slideshow video template when it is silent (motion + transitions only, no voice-over). A render for a form node is not done until it is attached to that node. Pass node_id (and form_id) so the completed render attaches itself automatically - do not poll clipform_check_render to completion or manually chain clipform_upload_media_asset + clipform_attach_node_media; fire the render and move on.

  Connector

• view_dxf

  Aspicio

  Open an interactive viewer the user can pan, zoom, and toggle layers in (renders in-chat on MCP Apps-capable hosts). Reads DXF and vector PDF; for a PDF it shows line work and text rather than a page facsimile, so images, shadings, and transparency are absent by design. Use this when the user wants to see or explore the drawing themselves; for your own analysis use a describe_* tool (facts) or a render_* tool (image). The viewer shows only the drawing from this call. Delivery is handled by the widget itself: small drawings are embedded in the result and larger URL-sourced drawings are fetched by the widget through its own tool call — never re-fetch or inline the file for the viewer's sake, and don't blind-retry if the user reports an empty viewer (the viewer posts its actual status back to the conversation context).

  Connector