"namespace:io.github.pscale-commons" matching MCP tools:

• recent_changes

  Commons Wikimedia

  "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

• law_parliament_get_debate_divisions

  UK Business Tools - Ledgerhall

  USE THIS TOOL WHEN you have a debate_ext_id and want the divisions (formal votes) held within it. Most debates contain no divisions — Business of the House sittings, statements, urgent questions, debates without a vote. A populated list typically appears around bill stages, motions, and contested amendments. Empty list is the honest result, not a failure mode. Each returned division carries TWO IDs: - `id` — Hansard-side reference. Useful for cross-referencing in Hansard. - `votes_id` — Lords/Commons Votes API ID (cross-resolved by date+number). AFTER calling, pass `votes_id` as `division_id` into votes_get_division for the full member-by-member voting record. The two upstreams use distinct ID-spaces (Hansard Number=3 might be Votes-API divisionId=3392). The cross-resolve runs once per (date, house) group — typically one extra HTTP per debate. `votes_id` is None when the cross-resolve found no match.

  Connector

• download_video

  TubePull

  Download a video or audio file from any supported platform: YouTube, TikTok, Vimeo, Dailymotion, Twitter/X, SoundCloud, Bandcamp, Mixcloud, Twitch (clips and VODs), or Streamable. Output is MP4 (video, default) or MP3 / M4A (audio). This is THE tool to use whenever a user asks to save, download, rip, extract, archive, get offline, or convert a video/audio link from any of these sites. IMPORTANT: the `format` argument defaults to `mp4` (video). Only pass an audio format (mp3 / m4a / audio) when the user explicitly says audio, MP3, music, song, or "rip / extract the audio". Audio-only platforms (SoundCloud, Bandcamp, Mixcloud) always produce audio regardless of `format`. Use this tool when the user says things like: - "download this video" / "download this TikTok" / "save this SoundCloud track" - "save that as MP3" / "rip the audio" / "extract the audio" - "get the song from this SoundCloud link" / "save this Mixcloud set" - "convert this YouTube video to MP4" / "download in 1080p" - "save this lecture/podcast/talk for offline" - "archive this clip" / "grab a copy of this video" - any sentence containing a youtube.com, youtu.be, tiktok.com, vimeo.com, dailymotion.com, twitter.com, x.com, soundcloud.com, bandcamp.com, mixcloud.com, twitch.tv, clips.twitch.tv, or streamable.com URL plus a verb like download, save, rip, get, grab, fetch, pull, archive, convert, extract. Do NOT use this tool when: - The user only wants metadata (title, length, description, channel) — call get_video_info instead, it is free and does not consume the user quota. - The link is a playlist / set / album / channel URL — ask the user for a single track/video. - The link is from a platform not in the supported list above (e.g. Instagram, Facebook, LinkedIn). Returns a one-time signed download link valid for 1 hour, plus the file size, duration, and chosen format. Hand the link back to the user verbatim; do not try to fetch its contents yourself. Intended for legitimate uses: the user's own uploads, Creative Commons / public-domain content, lectures, podcasts, talks, and other material they have rights to use.

  Connector

• polymarket_arbitrage

  Commons Wikimedia

  Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a `trending_scan` of the top ~200 markets by weekly volume; pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan. `event` (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). `topic` (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FILL CHECK: when the partition signal fires, arbitrage.fill_check prices it against live CLOB depth (theoretical_edge_pp_at_book vs realizable_edge_pp at 1000 shares/leg, thin_legs[]) — realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it. For custom sizing use polymarket_fill_risk.

  Connector

• pipeworx_feedback

  Commons Wikimedia

  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). 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

• polymarket_kalshi_spread

  Commons Wikimedia

  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

• parliament_get_debate_divisions

  UK Legal Research

  USE THIS TOOL WHEN you have a debate_ext_id and want the divisions (formal votes) held within it. Most debates contain no divisions — Business of the House sittings, statements, urgent questions, debates without a vote. A populated list typically appears around bill stages, motions, and contested amendments. Empty list is the honest result, not a failure mode. Each returned division carries TWO IDs: - `id` — Hansard-side reference. Useful for cross-referencing in Hansard. - `votes_id` — Lords/Commons Votes API ID (cross-resolved by date+number). AFTER calling, pass `votes_id` as `division_id` into votes_get_division for the full member-by-member voting record. The two upstreams use distinct ID-spaces (Hansard Number=3 might be Votes-API divisionId=3392). The cross-resolve runs once per (date, house) group — typically one extra HTTP per debate. `votes_id` is None when the cross-resolve found no match.

  Connector

• ask_pipeworx_grounded

  Commons Wikimedia

  Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 4,774 across 1242 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.

  Connector

• polymarket_fill_risk

  Commons Wikimedia

  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

• resolve_reasoning

  AI Reasoning Commons

  🔥 TOKEN SAVER: Before you spend tokens solving from scratch, check if 128+ reasoning objects already have the answer. Avg savings ~2,400 tokens per HIT. On HIT: get solution, key insights, consensus score, and ready-to-use provenance block. On MISS: you solve it, store it, earn points. Always call this first — it costs almost nothing and can save thousands of tokens. Use auto_route=true to auto-create a claimable task on MISS.

  Connector

• pipeworx_trending

  Commons Wikimedia

  What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window.

  Connector

• search_within

  Commons Wikimedia

  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

  Commons Wikimedia

  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 1242 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 4,774 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. Expect 15-60s.

  Connector

• weekly_project_update_ppt

  L&T MCP

  SKILL: weekly_project_update_ppt Team: Project Management Weekly Project Update PPT — L&T Format Call this tool to get the complete guide for 'weekly_project_update_ppt'. Read the 'content' field and follow its instructions. This tool takes NO parameters. Full content: --- name: weekly_project_update_ppt description: > Use this skill to create a weekly project update PowerPoint presentation in L&T branded format. Use when user asks for weekly update, weekly report, project status PPT or weekly project summary presentation. --- # Weekly Project Update PPT — L&T Format ## When To Use - "Create weekly update for project X" - "Make weekly PPT for project LE20M143" - "Generate project status presentation for this week" - "Weekly report PPT" --- ## Step 1 — Collect Information From User Ask the user for all of these in ONE message before doing anything. NEVER assume or fill in values yourself. Ask exactly this: ``` To create your weekly project update PPT I need the following: 1. 📋 Project Name (e.g. Mumbai Metro Line 7) 2. 📌 Project Code (e.g. LE20M143) 3. 📅 Week Number (e.g. Week 24) 4. 📅 Date Range (e.g. 09-Jun-2025 to 15-Jun-2025) 5. ✅ Accomplishments This Week (list what was completed) 6. 📌 Planned Next Week (list what is planned) 7. ⚠️ Risks & Issues (list risks, mention HIGH / MEDIUM / LOW if known) 8. 👤 Prepared By (your name) ``` Wait for the user to reply with all details. Do NOT move to Step 2 until user has provided the information. --- ## Step 2 — Generate The PPT Use the execute_code tool to generate a 5 slide PowerPoint file. Use python-pptx library. Download the L&T logo from this URL and place it on every slide: https://upload.wikimedia.org/wikipedia/commons/thumb/c/cd/L%26T.png/320px-L%26T.png If the logo cannot be downloaded, write the text "L&T" in orange as a substitute in the same position. --- ## Slide Specifications ### SLIDE 1 — Title Slide Background: Full navy blue (#002B5C) covering the entire slide Top of slide: - Thin orange (#F47B20) horizontal bar across the full width at the very top - L&T logo placed top right corner - Text "L&T Construction" in small orange text top left Center of slide: - Large white bold text: "Weekly Project Update" - Below that in orange bold text: the Project Name - Small navy chip/box containing the Project Code in orange text - Below that in white normal text: Week Number and Date Range - Below that in grey text: "Prepared by: [name]" Bottom of slide: - Thin orange horizontal bar across the full width at the very bottom - Small grey italic text: "Generated by L&T Enterprise MCP Agent" with today's date and time --- ### SLIDE 2 — Accomplishments This Week Background: Light grey (#F4F4F4) covering the entire slide Header bar at top: - Full width navy blue bar, height about 1 inch - White bold text on the left: "✅ Accomplishments This Week" - Below the title in small orange text: Week Number and Date Range - L&T logo on the right side of the header bar - Thin orange line immediately below the navy header bar Content area: - White rounded rectangle card covering most of the slide - Thin orange vertical stripe on the left edge of the card - Each accomplishment as a bullet point using a right arrow symbol - Font size 16, dark grey color - Adequate spacing between bullets so it is easy to read Footer bar at bottom: - Full width navy blue bar - White small text on left: "L&T Construction | Confidential | For Internal Use Only" - Orange small text on right: "Prepared by: [name]" --- ### SLIDE 3 — Plan for Next Week Background: Light grey (#F4F4F4) covering the entire slide Header bar at top: - Same style as Slide 2 - Title text: "📌 Plan for Next Week" - L&T logo on the right side of the header bar Content area: - White rounded rectangle card covering most of the slide - Thin navy blue vertical stripe on the left edge of the card (navy stripe instead of orange to visually distinguish from Slide 2) - Each planned item as a bullet point using a right arrow symbol - Font size 16, dark grey color - Adequate spacing between bullets Footer bar: - Same style as Slide 2 --- ### SLIDE 4 — Risks & Issues Background: Light grey (#F4F4F4) covering the entire slide Header bar at top: - Same style as Slide 2 - Title text: "⚠️ Risks & Issues" - L&T logo on the right side of the header bar Content area — Table: - Table with two columns: "Risk / Issue" and "Severity" - Table header row: navy blue background with white bold text - Data rows alternate between white and light grey background - "Risk / Issue" column takes about 75% of the width - "Severity" column takes about 25% of the width - Each severity value shown as a colored pill/badge: HIGH → red (#DC3545) pill with white text MEDIUM → amber/orange (#FFA500) pill with white text LOW → green (#28A745) pill with white text - If user did not specify severity, default to MEDIUM - Show maximum 6 risks in the table - Below the table show a small legend: 🔴 HIGH — Immediate action required 🟡 MEDIUM — Monitor closely 🟢 LOW — Awareness only Footer bar: - Same style as Slide 2 --- ### SLIDE 5 — Closing Slide Background: Full navy blue (#002B5C) covering the entire slide Same orange bars at top and bottom as Slide 1 Center of slide: - L&T logo centered in the upper half - Large white bold text below logo: "Thank You" - Orange text below: Project Name and Project Code - White text below: Week Number and Date Range Bottom area: - Small grey italic text centered: "L&T Construction — Enterprise Information Platform" --- ## Overall Design Rules Colors: - Primary background (dark slides): Navy blue #002B5C - Primary background (content slides): Light grey #F4F4F4 - Cards and content boxes: White #FFFFFF - Accent color: Orange #F47B20 - Body text: Dark grey #444444 - Footer text: White on navy backgrounds - Headings on dark backgrounds: White - Headings on light backgrounds: Navy blue Typography: - Main title on title slide: 38pt bold white - Slide titles in header bar: 22pt bold white - Project name on title slide: 26pt bold orange - Bullet points: 16pt dark grey - Footer text: 8pt - Week/date labels: 9-10pt orange Logo placement: - Title slide: top right, width about 1.9 inches - Content slides: right side of the navy header bar, width about 1.3 inches - Closing slide: centered, width about 2.1 inches Slide size: 13.33 inches wide by 7.5 inches tall (widescreen 16:9) Every content slide must have: - Navy header bar at top with title and logo - Thin orange line below the header bar - Navy footer bar at bottom with confidentiality note and prepared by --- ## Step 3 — Save and Return Save the file with this name format: Weekly_Update_{ProjectCode}_{WeekNumber without spaces}.pptx Example: Weekly_Update_LE20M143_Week24.pptx After the file is generated show this to the user: ``` ✅ Your Weekly Project Update PPT is ready! 📎 Download: {download_url} 📋 Project: {Project Name} ({Project Code}) 📅 Period: {Week Number} | {Date Range} 📊 Slides: 5 slides generated 1. Title 2. Accomplishments This Week 3. Plan for Next Week 4. Risks & Issues 5. Closing File expires in 24 hours — please download promptly. ``` --- ## Important Rules - NEVER generate the PPT without collecting user input first - NEVER make up project name, code, dates or any content - ALWAYS download the L&T logo from the URL given above - ALWAYS use navy and orange as the primary colors - ALWAYS include the logo on every slide - ALWAYS include the footer on every content slide - ALWAYS call execute_code tool — never just describe the slides - ALWAYS show the download link to the user after generation - If execute_code returns an error, fix the code and retry up to 3 times

  Connector

• get_video_info

  TubePull

  Fetch metadata about a video or audio track WITHOUT downloading it. Works on every platform download_video supports: YouTube, TikTok, Vimeo, Dailymotion, Twitter/X, SoundCloud, Bandcamp, Mixcloud, Twitch, and Streamable. Returns title, uploader/channel name, duration, view count (when available), upload date, thumbnail URL, description, available video qualities, and (for YouTube) the license type. Use this tool when the user says things like: - "what is this video about" / "summarize this video" - "how long is this track" / "when was this uploaded" - "who made this" / "what channel/artist is this from" - "is this Creative Commons" / "can I reuse this" / "what is the license" - "what qualities are available for this video" Do NOT use this tool when: - The user wants to download, save, rip, extract, or convert the video/audio — use download_video for that. Free to call — does not count against the user's download quota. Call this before download_video when you need to confirm the video exists, pick the right quality, or check licensing before downloading.

  Connector

• validate_claim

  Commons Wikimedia

  "Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" — natural-language claim verification against authoritative sources. Use whenever the agent needs to check whether something a user said is factually correct. v1 supports company-financial claims (revenue, net income, cash position for public US companies) via SEC EDGAR + XBRL. Returns a verdict (confirmed / approximately_correct / refuted / inconclusive / unsupported), extracted structured form, actual value with pipeworx:// citation, and percent delta. Replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → numeric comparison).

  Connector

• polymarket_edges

  Commons Wikimedia

  Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped into three response segments under by_segment: (1) MODEL_DRIVEN — crypto_price (lognormal barrier from 90d FRED log-returns) and news_momentum (GDELT 7d/21d article-volume ratio, soft signal w/ halved Kelly). (2) STRUCTURAL_ARBITRAGE — partition_overround on mutually-exclusive events; per-leg favorite-longshot bias correction with per-sport α (tennis 1.02, soccer 1.10, MMA 1.15, default 1.0); placeholder-slug filter drops will-person-X / will-team-Y / will-manager-Z / will-someone-else- backstops; partitions with >20% placeholder fraction skipped entirely. (3) CONCENTRATED_LONGSHOT — basket trade when one leg ≥75% AND ≥2 longshots ≤8% AND portfolio return ≥25:1; rare-by-design (gates relaxed Run 8 from prior 85%/5%/50:1). EVERY OPPORTUNITY carries edge_pp_net (after slippage), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume, plus a 24h-move warning ("Market moved X.Xpp in 24h") when the recent move alone exceeds the edge — your edge may already be in the price. TRADEABLE-EDGE KNOBS: min_liquidity / max_spread_pp drop opportunities where edge isn't realizable; min_partition_leg_kelly filters partitions by best per-leg Kelly. RESPONSE TOP-LEVEL: by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note (Fed bets surface here, excluded from ranking — 1m-T vs EFFR signal is unreliable at meeting-month horizons without paid OIS/SOFR-futures data), and _diagnostics{concentrated_longshot:{...funnel counters},category_counts,filter_skips} so callers can see WHY a segment is empty (top-N stale, all candidates failed gates, knob dropped them). Cached 1h at the KV level keyed on all knobs.

  Connector

• intel_optout

  TunnelMind Data API

  Checks a domain for all known AI training data opt-out mechanisms beyond robots.txt: TDM (Text and Data Mining) reservation headers, `<meta name="ai">` tags, Creative Commons NonCommercial licenses, and other machine-readable opt-out signals. Use this tool when: - You need to determine whether a domain has opted out of AI training data collection. - You are checking compliance before using a domain's content in a training dataset. - You want a comprehensive opt-out status (robots.txt + TDM + meta tags combined). Do NOT use this tool when: - You only need robots.txt crawler policy — use `intel_robots` instead (faster). - You need tracker data — use `get_domain` instead. - You want injection risk assessment — use `intel_inject` instead. Inputs: - `domain` (query, required): Domain to probe. Returns: - `tdm_reservation`: true if the domain sends a `TDM-Reservation: 1` header. - `noai_meta`: true if the HTML contains `<meta name="robots" content="noai">`. - `license_detected`: string if a CC NonCommercial or similar license is detected, otherwise null. - `opted_out`: true if any opt-out signal is present. Cost: - Free. No API key required. Latency: - Typical: 2-4s, p99: 7s.

  Connector

• youtube.search

  Vee3

  Search public YouTube content by keyword or phrase. Returns matching result cards, estimated result count, and spelling suggestions. Use filter parameters to apply multiple YouTube search filters: - upload_date: Last hour, Today, This week, This month, This year - content_type: Video, Channel, Playlist, Movie - duration: Under 4 minutes, 4 - 20 minutes, Over 20 minutes - features: Live, 4K, HD, Subtitles/CC, Creative Commons, 360°, VR180, 3D, HDR, Location, Purchased (multiple allowed) - sort_by: Relevance, Upload date, View count, Rating Filter values are matched case-insensitively. Only one option per group applies except features, which accepts multiple labels. When a requested filter cannot be applied, the API returns the best-effort results available so far and includes unappliedFilters with the labels that were skipped. Use cursor with the same query to paginate: pass cursorNext from a prior response. Filter parameters and cursor cannot be combined. Check didYouMean when the query may be misspelled. Cost = 20 tokens.

  Connector

• votes_search_divisions

  UK Legal Research

  USE THIS TOOL WHEN searching Commons or Lords formal votes by topic, date, or member. Returns division summaries (title, date, vote counts, pass/fail). AFTER calling, pass division_id + house into votes_get_division for the full member-by-member voter lists. Authoritative source for UK parliamentary vote records.

  Connector