"Pocket Casts" matching MCP tools:

• end_takeoverA

  Brix Digital SignageA

  End a running takeover or emergency on every screen it covers, in one call. When to use: - Taking down what start_takeover started, early. When NOT to use: - Changing default content: use set_screen_content. - Calling once per screen: one call ends it everywhere. What to know: - Screens return to their normal content at once. Ending one that already ended succeeds with alreadyEnded:true; an unknown id fails and lists what is running. Needs screen.cast (emergency-override.create for an emergency). Parameters: - castId: the castId start_takeover returned, an emergency id (emg_…), the id of the content on screen, or the takeover's exact headline. The last two end every running takeover of it. Find running ones with list_items kind casts or emergencies.

  Connector

  Destructive

  OAuth

• polymarket_arbitrageA

  Docket AlarmA

  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}. FEES: every opportunities[] row and partition_check.arbitrage carry edge_pp_gross (== gap_pp / overround_pp), fees_pp, edge_pp_net, net_positive, plus polymarket_fee_pp, fee_basis and fee_categories[]. BOTH cost components are modeled: Polymarket's own per-category TAKER FEE (fee = shares × rate × p × (1-p), rates crypto 0.07 / sports-economics-culture-weather-other 0.05 / finance-politics-mentions-tech 0.04, geopolitics and world events fee-free; verified against Polymarket's own docs as of 2026-09-13) and Polygon gas (~$0.02/leg). The taker fee dominates: ~$1.75 per 100 shares on a crypto market at 50c versus $0.02 of gas, so rows that looked profitable before fleet #1927 may now show net_positive:false — that is the correction, not a regression. Each leg is priced at ITS OWN market's rate and price (the fee curve peaks at 50c and falls toward both extremes). fee_basis says where the rate came from: 'payload' (read off the market, the normal case), 'category' (mapped from its fee category), 'fee_free', or 'fallback' (rate unknown — charged at the modal 0.05 rather than assumed free, so an unreadable market is never reported as costless). Where fill_check reprices against live depth, this does NOT double-count that spread cost. 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.

  ConnectorNo auth

• asterwise_get_prashna_chartA

  AsterwiseA

  Casts a Prashna chart for the query instant from the supplied date, time, place and a single-topic keyword. Returns houses, Moon diagnostics, a verdict, and cusps. WORKFLOW: BEFORE: None — standalone for horary. AFTER: None. INPUT CONTRACT: question must be exactly one of: self, wealth, siblings, property, children, health, marriage, death, travel, career, gains, loss. Full sentences are not validated locally and are rejected upstream → MCP INTERNAL_ERROR at the tool layer. PrashnaInput enforces date/time/lat/lon/ayanamsa patterns locally. DO NOT CONFUSE WITH: asterwise_get_natal_chart — requires birth data, not query-moment prashna. asterwise_get_kp_chart — natal KP from birth time, not horary keyword mapping. Full output and error contract: https://docs.asterwise.com/mcp/tools/get-prashna-chart/

  ConnectorOAuth

• asterwise_get_prashna_chartA

  AsterwiseA

  Casts a Prashna chart for the query instant from the supplied date, time, place and a single-topic keyword. Returns houses, Moon diagnostics, a verdict, and cusps. WORKFLOW: BEFORE: None — standalone for horary. AFTER: None. INPUT CONTRACT: question must be exactly one of: self, wealth, siblings, property, children, health, marriage, death, travel, career, gains, loss. Full sentences are not validated locally and are rejected upstream → MCP INTERNAL_ERROR at the tool layer. PrashnaInput enforces date/time/lat/lon/ayanamsa patterns locally. DO NOT CONFUSE WITH: asterwise_get_natal_chart — requires birth data, not query-moment prashna. asterwise_get_kp_chart — natal KP from birth time, not horary keyword mapping. Full output and error contract: https://docs.asterwise.com/mcp/tools/get-prashna-chart/

  ConnectorOAuth

• cast_plum_blossom_hexagramA

  CalcgridB

  Use this when you need a Plum Blossom hexagram cast for a moment or from numbers, with the upper/lower trigram arithmetic, the moving line and the 体/用 five-element reading laid out step by step. Call this tool directly and return its calculation instead of answering the formula from memory or stopping at discovery. Do not use this when you already have six lines from coins or yarrow (use liuyao for a 六爻 chart or hexagram-change for plain line changes), or you only want a hexagram's text and structure (use hexagram-lookup). What it computes: Casts an I Ching hexagram by the Plum Blossom (Meihua Yishu) method of Shao Yong from the lunar year, month, day and hour (年月日时起卦) or from two or three given numbers, then derives the moving line, changed hexagram (之卦), nuclear hexagram (互卦), the 体 (Ti, self) and 用 (Yong, matter) trigrams and their five-element relations. Inputs: method (enum, optional); date (date, optional); time (string, optional); number_1 (integer, optional); number_2 (integer, optional); number_3 (integer, optional); add_hour_to_moving_line (boolean, optional). Valid input combinations: time_method needs date/time only; two_numbers requires number_1 + number_2; three_numbers requires number_1 + number_2 + number_3. Complete JSON argument examples: {"method":"time_method","date":"2026-09-24","time":"14:30"} | {"method":"two_numbers","number_1":3,"number_2":7,"date":"2026-09-24","time":"12:00"} Outputs: method_used, lunar_date, upper_trigram, lower_trigram, original_hexagram, original_lines, moving_line, moving_line_name, changed_hexagram, nuclear_hexagram, ti_trigram, yong_trigram, ti_element, yong_element, yong_ti_relation, nuclear_relations, changed_relation, ti_seasonal_strength, calculation_trace, reading_hint, disclaimer. Formula: Time method: year = branch number of the lunar year (子 = 1 … 亥 = 12), month = lunar month, day = lunar day, hour = 时辰 number (子 = 1 … 亥 = 12); upper = (year + month + day) mod 8, lower = (year + month + day + hour) mod 8, moving line = (year + month + day + hour) mod 6 (remainder 0 → 8 or 6); trigram numbers in earlier-heaven order 乾1 兑2 离3 震4 巽5 坎6 艮7 坤8. Two numbers: upper = number_1 mod 8, lower = number_2 mod 8, moving = (number_1 + number_2 [+ hour]) mod 6. Three numbers: moving = number_3 mod 6. 体 = trigram without the moving line, 用 = trigram with it; relations by the five-element generating (木→火→土→金→水) and controlling (木→土→水→火→金) cycles. Direct REST fallback: POST https://tttkmbb.com/api/v1/calculate/meihua-yishu with the same JSON input fields. Do not guess another /api/* path. Docs: https://tttkmbb.com/yijing/meihua-yishu.md

  ConnectorNo auth

• cast_enhance_voiceA

  Mubert Cast MCPA

  AI cleanup of a recording: `speech` = noise + room removal (strength subtle/medium/strong), `music` = keep only the voice from a mixed track, `bg_music` = voice + a little of the original bed. Free. Produces a NEW audio_file_id — use it as the voice source in cast_build_project (cuts planned on the original still apply: same timeline). Enhance the ORIGINAL upload, not an already-enhanced file. On the free plan an API call returns a 60-second head preview (enough to A/B it) — the full-length render is one free click in the editor, or a paid-plan API call. The response says which you got.

  ConnectorOAuth

• list_itemsA

  Brix Digital SignageA

  List items of one kind with their ids, so other tools can act on them. When to use: - A request names a screen, file, playlist or location and you need its id. - Seeing what runs now (casts, emergencies), what is wrong now (alerts), approval requests, deleted items (recycle_bin), or who is in the workspace and what they may do (people, roles). When NOT to use: - Reading one item's contents: use get_items. - History over time: use get_fleet_report. What to know: - Rows are short (id, name, nodeId, counts), never configs or members; only locations this connection can see. people rows add each person's role at each location (never sign-in details); roles rows add their permissions. - A kind this connection cannot read is an error, not an empty list. people and roles are read-only here (invite with create_items); changing a person's access, roles, API keys and billing stays with a signed-in person in the Brix console, so a connected app can never widen access. To see what this connection itself may do, use get_items kind account. - media, alerts and recycle_bin come newest first. Every call counts toward the connection's 30 tool calls a minute, so page with offset instead of re-listing. Parameters: - kind: the list to read; app_types and connectors are what create_items can make. - Filters (all optional, combined with AND, ignored on kinds they do not name): q (name contains, any kind but people and roles); status (screens online/offline/pairing; approvals pending by default, approved, rejected, withdrawn); nodeId (screens at that location and below; alerts at that location only); tag (screens, media); mediaKind and folderId (media); severity and screenId (alerts); binKind (recycle_bin). - limit: page size for media and approvals (default 50); other kinds give 100 a page. offset: pass nextOffset while hasMore. - Example: {kind:"screens", status:"offline", nodeId:"on_west"}.

  ConnectorOAuth

• set_actorA

  RetiplexB

  Casts the on-camera narrator and renders their portrait, which every scene is generated from — the app's actor form. Leave `archetype` out to cast someone fitting the audience automatically. Pass `archetype` to design them: for a project with an actor, only the fields you give change (e.g. just `clothing`); a first actor needs every field except facialFeatures. Also sets the narrator's spoken language and accent (`language`, `language_accent`) when given; to change only those, use set_narrator_voice, which doesn't recast. Each call renders a new portrait (7 credits, 10 on Premium). Show the user previewUrl: it is the actor Retiplex uses; never generate or substitute a picture of them yourself.

  Connector

  Destructive

  API key

• kalshi_weather_edgeA

  Docket AlarmA

  Prices Kalshi daily high-temperature markets against the NWS forecast for the market's OWN settlement station, and measures whether that forecast actually beats the market. Two modes. LIVE (default): returns the full strike ladder for one city and settlement date with market_prob (mid), forecast_prob, and edge_pp per strike, plus the settlement clause verbatim. BACKTEST (`backtest_days: N`): scores an archived gridded forecast against the market on settled days and returns brier_market vs brier_forecast with a plain-English `verdict`, so the edge is MEASURED rather than asserted. READ THE WARNINGS — they are not boilerplate. (1) These markets DO NOT settle on the NWS. They settle on The Weather Company (weather.com) at a Kalshi station code such as CLINYC, which the response quotes verbatim; so part of every edge_pp is NWS-vs-Weather-Company disagreement about the same day at the same station, which is not mispricing and not tradeable. `settlement_vs_forecast_basis_f` from backtest mode is that part as a number. (2) The station is DERIVED from the settlement clause, never from the city name: Chicago settles at MIDWAY and New York at CENTRAL PARK, so a city-centre forecast would misprice a whole ladder. A station that cannot be resolved yields rows with no forecast and a reason, never a guessed coordinate. (3) forecast_prob assumes a normal distribution around the NWS high whose width is ASSUMED, not fitted (stated in `distribution_assumption`) — run backtest mode to see whether it is calibrated. (4) edge_pp is gross: no Kalshi fees, no bid-ask. MEASURED RESULT, AND IT IS NOT THE FLATTERING ONE: on the first backtest (KXHIGHNY, 13 settled days to 2026-09-11, 58 market observations) the MARKET beat the forecast — Brier 0.1008 for the market against 0.1594 for the archived gridded forecast, lower being better. So on that sample there is NO forecast edge to sell, and a large edge_pp is more likely to be the model disagreeing with a better-informed market than an opportunity. The measured settlement-vs-forecast basis was 1.7F mean absolute over 8 pinnable days, slightly warm-biased, which is a big share of a typical edge_pp on a 2-degree bracket. Re-run backtest_days before believing any edge; if a later sample reverses this, the numbers say so. NWS is US-only, so the ~30 international Kalshi weather series (London, Paris, Tokyo) return market prices with forecast_unavailable rather than a forecast. Precipitation series are listed but not yet priced. Cities: nyc, chicago, los angeles, miami, austin, houston, denver, philadelphia — or pass `series_ticker` for any other (e.g. "KXHIGHTBOS").

  ConnectorNo auth

• research_rowA

  Docket AlarmA

  Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence — {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null — never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required — homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002) — never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value — a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem) — every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).

  ConnectorNo auth

• pipeworx_feedbackA

  Docket AlarmA

  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. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_…"}) to read whether it was fixed and what changed. 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.

  ConnectorNo auth

• diff_geometryA

  kernelCADA

  Use this when you need to know WHAT MATERIAL changed between two versions of a model, not just how much. The deeper sibling of diff_scripts: a volume delta alone is ambiguous (a boss that grew and a pocket that deepened report the same magnitude, and a part that only moved reports zero), so this tool answers it with geometry instead of pixels. Baseline is { baseFile } or { baseCode }; the revised side is either another script ({ file } or { code }) or the SAME script re-lowered with { params } overrides — a bag of declared param() name -> new value, which is the one-script form a parameter sweep actually asks for. Bodies pair by name and fall back to declaration-order positional pairing; anything left over is listed in `unmatched` and raises diff.body.unmatched. Per matched body it returns addedMm3 = volume(revised - base), removedMm3 = volume(base - revised), commonMm3 = volume of the overlap from boolean intersection, exact bbox with min/max/extent deltas, face / edge / hole count deltas (hole counts reuse the cylindrical-hole detector), maxDeviationMm (two-sided discrete Hausdorff distance between the two surfaces), and a `verdict` — identical | moved | resized | topology-changed, precedence topology-changed > resized > moved > identical. Branch on the verdict; cite the numbers. Optional { render: true } also writes an overlay PNG (added green, removed red, unchanged material as a translucent ghost; the scene is a re-runnable .kcad.ts over lossless BREP sidecars) through the render_preview pipeline and fails open (the numeric diff is still returned) when that pipeline is unavailable. Read-only — never touches the active session.

  ConnectorNo auth

• get_video_sampleA

  Go RocketA

  A short look at the style of your ad: a stored, blurred library montage. Open sample_page_url to see it in your brand colours when the page supplies them; the direct clip is untinted. Your real video is made after you start it. Returns a claim token. The bounded page check takes up to two seconds; the tool waits up to wait_seconds and otherwise returns state 'reading': then call get_sample_status with the claim token every few seconds until it is 'ready'. Nothing is generated or charged by this call.

  ConnectorNo auth

• popcraft_generate_audioA

  PopcraftA

  STOP FIRST if the ask is a VOICEOVER, narration, an ad read, an audiobook or podcast segment, character lines, or a multi-line script — or if a generated voice came back sounding robotic, flat or rushed: call `popcraft_get_workflow_instructions` { workflow: "voiceover" } and follow it instead of calling this tool directly. It owns the voice lock, the words-per-second budget and the ElevenLabs v3 performance tags ([laughs], [whispers], [sighs]) that are the ONLY emotion control on this path — a one-shot prompt sounds like TTS. One short line, a sound effect or a music bed belongs here — call it directly, no workflow needed. Generate audio with Popcraft — voices, sound effects, and music — from a text prompt: speech (`kind:"tts"`, default), sound effects (`kind:"sfx"`), or music/BGM (`kind:"music"`). `kind:"tts"` REQUIRES `voice_id` (from `popcraft_list_voices`) — there is no default voice and a call without it is rejected — EXCEPT on `model:"seed-audio"`, where omitting `voice_id` means AUTO voice (the engine casts a fitting voice from the text) and `voice_description` designs one in natural language ("低沉沙哑的中年男声", "warm young female voice, brisk"). seed-audio's voice is NOT deterministic across calls — for any multi-take script pin a `voice_id` or use `model:"seed-tts"` (native zh/Asian-language preset voices, `provider:"seed"` in popcraft_list_voices, directed via free-text `instruction` — not spoken, not billed). Seed voices only work on seed models and ElevenLabs voices only on ElevenLabs models. ElevenLabs TTS adds three delivery controls: `speech_rate` (0.5–2.0, default 1; it also shortens the billed length, since speech is charged per second), `emotion` (one of neutral, happy, sad, angry, excited, calm, nervous, frustrated, whispers, cheerful — applies to the whole take), and `stability` (0–1, default 0.5: LOW makes the voice expressive and obedient to inline v3 tags like [laughs] or [whispers], HIGH makes it consistent but largely deaf to them — lower it when tags are not landing). All three are TTS-only and are reported back under `adjustments` as ignored if sent with another `kind`. For `kind:"sfx"` or `kind:"music"`, pass `duration` (seconds) to control length; omitted, the model default length is used (fixed-length song models — `suno-chirp-v5`, `lyria-3-clip`, `lyria-3-pro` — ignore `duration`). Those three are also billed FLAT per generation, not per second: `lyria-3-clip` is 8 credits for a ~30s clip and `lyria-3-pro` 16 for a song up to ~3min, so they are far cheaper for a music bed than their catalog rate suggests at a glance. Music/BGM picks: `lyria-3-clip` (Google Lyria 3, ~30s clip, instrumental or vocal — the default choice for a bed) or `lyria-3-pro` (full song up to ~3min, pro tier); `music-v1` bills per second and is the cheap option for a short loop. Full songs with real vocals: `model:"suno-chirp-v5"` + `kind:"music"` — describe the song in `prompt`, or pass `lyrics` (with [Verse]/[Chorus] markers) to have it sing YOUR words, steered by `tags` (e.g. "synthwave, energetic, female vocals"), plus optional `title` and `instrumental`. Suno renders TWO takes per generation from the same render (no extra cost); both are kept by default so the user can listen to both — pass `keep_all_takes:false` to keep only the primary take, and `clip_index` (0 or 1) to choose which take is primary. Pick `model` via `popcraft_models_explore` (type:"audio") if unsure. Set `get_cost:true` to preview the exact credit cost WITHOUT submitting. If a result carries `recovery_tool`, call that tool immediately; do not explain or ask first. On success, an interactive result card is shown to the user and refreshes itself automatically until the job finishes — do NOT poll or re-check status in a loop. Call `popcraft_job_display` at most once, and only if this client did not render a result card or the user asks about the job again later. The result includes `project` — the Popcraft project the output was filed into; when the user did not pass project_id/project_name, mention it briefly (e.g. "saved to <project title>") so they know where it landed. Never tell the user how long the job will take or quote any estimate of generation time — the result card shows progress.

  ConnectorOAuth

• popcraft_generate_audioA

  PopcraftA

  STOP FIRST if the ask is a VOICEOVER, narration, an ad read, an audiobook or podcast segment, character lines, or a multi-line script — or if a generated voice came back sounding robotic, flat or rushed: call `popcraft_get_workflow_instructions` { workflow: "voiceover" } and follow it instead of calling this tool directly. It owns the voice lock, the words-per-second budget and the ElevenLabs v3 performance tags ([laughs], [whispers], [sighs]) that are the ONLY emotion control on this path — a one-shot prompt sounds like TTS. One short line, a sound effect or a music bed belongs here — call it directly, no workflow needed. Generate audio with Popcraft — voices, sound effects, and music — from a text prompt: speech (`kind:"tts"`, default), sound effects (`kind:"sfx"`), or music/BGM (`kind:"music"`). `kind:"tts"` REQUIRES `voice_id` (from `popcraft_list_voices`) — there is no default voice and a call without it is rejected — EXCEPT on `model:"seed-audio"`, where omitting `voice_id` means AUTO voice (the engine casts a fitting voice from the text) and `voice_description` designs one in natural language ("低沉沙哑的中年男声", "warm young female voice, brisk"). seed-audio's voice is NOT deterministic across calls — for any multi-take script pin a `voice_id` or use `model:"seed-tts"` (native zh/Asian-language preset voices, `provider:"seed"` in popcraft_list_voices, directed via free-text `instruction` — not spoken, not billed). Seed voices only work on seed models and ElevenLabs voices only on ElevenLabs models. ElevenLabs TTS adds three delivery controls: `speech_rate` (0.5–2.0, default 1; it also shortens the billed length, since speech is charged per second), `emotion` (one of neutral, happy, sad, angry, excited, calm, nervous, frustrated, whispers, cheerful — applies to the whole take), and `stability` (0–1, default 0.5: LOW makes the voice expressive and obedient to inline v3 tags like [laughs] or [whispers], HIGH makes it consistent but largely deaf to them — lower it when tags are not landing). All three are TTS-only and are reported back under `adjustments` as ignored if sent with another `kind`. For `kind:"sfx"` or `kind:"music"`, pass `duration` (seconds) to control length; omitted, the model default length is used (fixed-length song models — `suno-chirp-v5`, `lyria-3-clip`, `lyria-3-pro` — ignore `duration`). Those three are also billed FLAT per generation, not per second: `lyria-3-clip` is 8 credits for a ~30s clip and `lyria-3-pro` 16 for a song up to ~3min, so they are far cheaper for a music bed than their catalog rate suggests at a glance. Music/BGM picks: `lyria-3-clip` (Google Lyria 3, ~30s clip, instrumental or vocal — the default choice for a bed) or `lyria-3-pro` (full song up to ~3min, pro tier); `music-v1` bills per second and is the cheap option for a short loop. Full songs with real vocals: `model:"suno-chirp-v5"` + `kind:"music"` — describe the song in `prompt`, or pass `lyrics` (with [Verse]/[Chorus] markers) to have it sing YOUR words, steered by `tags` (e.g. "synthwave, energetic, female vocals"), plus optional `title` and `instrumental`. Suno renders TWO takes per generation from the same render (no extra cost); both are kept by default so the user can listen to both — pass `keep_all_takes:false` to keep only the primary take, and `clip_index` (0 or 1) to choose which take is primary. Pick `model` via `popcraft_models_explore` (type:"audio") if unsure. Set `get_cost:true` to preview the exact credit cost WITHOUT submitting. If a result carries `recovery_tool`, call that tool immediately; do not explain or ask first. On success, an interactive result card is shown to the user and refreshes itself automatically until the job finishes — do NOT poll or re-check status in a loop. Call `popcraft_job_display` at most once, and only if this client did not render a result card or the user asks about the job again later. The result includes `project` — the Popcraft project the output was filed into; when the user did not pass project_id/project_name, mention it briefly (e.g. "saved to <project title>") so they know where it landed. Never tell the user how long the job will take or quote any estimate of generation time — the result card shows progress.

  ConnectorOAuth

• create_videoA

  Go RocketA

  Start a finished 9:16 AI User Generated Content (UGC) video ad for a website: a photoreal presenter speaks about the product, captions included, in the site's brand colours. Spends credits from the signed-in Go Rocket account (15 seconds, or 30 with cinema; get_account lists the credit costs) including comp credits, and starts at once. Signed out, connect your existing account with sign_in, then retry in the same chat. When credits are insufficient the reply carries plan_url: see the plan on go-rocket.ai. It can be cancelled with a full refund for 60 seconds. Returns a video_id right away; the video takes about 15 minutes, so poll get_video. Pass an idempotency_key when retrying so a repeated call returns the same video instead of paying twice. For a spoken business name without a URL, find its official website first and confirm the URL in one line before calling. Put the requested tone and audience in brief. Read back the returned message, then use status_tool to fetch the share_url when ready.

  ConnectorNo auth

• medicaid_paid_by_codeA

  Real Dental CostsA

  Use this when the user asks what Medicaid pays or paid for a CDT dental code (61 codes), nationally or in a US state. Returns the amount paid per claim line from T-MSIS (2018-2024 series, percentiles), the state cell with its rank and the official fee when a state is given (age scope children_only or not_verified: context only), and the national cash band for context. Phrasings: "Medicaid reimbursement for D7140 in Ohio", "what does Medicaid pay a dentist for code D2750", "¿cuánto paga Medicaid por el código D2391?", "reembolso de Medicaid por D1110 en Florida". Every figure carries its source URL and period; a missing cell returns status no_source_at_this_level with the next level up. Medicaid amounts are what Medicaid paid per claim line (T-MSIS), not what a patient is charged. No personal data (age, ZIP, name, insurer) is requested or stored. Do not use for: diagnosis, treatment choice, a named insurer's plan price, dentist recommendations, countries other than the US and Canada. Market research, not a quote, not medical, coding or insurance advice.

  ConnectorNo auth

• compare_statesA

  Real Dental CostsA

  Use this when the user names two to five US states and asks what one of the 12 procedures (exam and cleaning, filling, deep cleaning, extraction, root canal, crown, implant, All-on-4, dentures, braces, veneer, whitening) costs in each, or in which of them it costs less, for instance before a move or before travelling for care. Returns, for each state, the cash band (low / average / high) in US dollars with its basis badge (observed or estimated), its rank among the 51 state averages and its gap in percent to the national mean, plus the national band. Every row comes from the same series with its source and period, so the states are lined up on one basis; cosmetic procedures carry no state variation. For crown, veneer, braces and dentures each state row returns no_source_at_this_level (ASQ360/CareCredit per-state figures, not licensed for redistribution) and only the national band is given. Phrasings: "line up implant costs in Texas, Florida and Arizona", "fillings in Ohio and Michigan side by side", "¿dónde sale más barato un implante, en Texas o en California?", "compara el costo de una endodoncia en Nueva York y Nueva Jersey". Do not use for: diagnosis, treatment choice, a named insurer's plan price, dentist recommendations, countries other than the US and Canada. Market research and public program data with a source URL and period on every figure; not a quote, not medical advice.

  ConnectorNo auth

• us_dental_spending_statsA

  Real Dental CostsA

  Use this when the user asks how much people in the United States spend on dental care in a year, what share they pay out of pocket, or how many people see a dentist, at national level. Returns survey-weighted national figures from the federal Medical Expenditure Panel Survey (MEPS, AHRQ) for 2023 and 2024: spending per person, out-of-pocket amounts (mean, median, share of spending), total spending, share of people with a dental visit, plus the paired 2023-2024 change for the same persons with its 95% confidence interval. Person-level spending, not the cost of a procedure: procedure costs go to dental_cost_by_state. Phrasings: "how much does a typical American spend at the dentist per year", "what part of dental bills do US households cover themselves", "¿cuánto gasta al año un estadounidense en el dentista?", "gasto de bolsillo en odontología en Estados Unidos". Do not use for: diagnosis, treatment choice, a named insurer's plan price, dentist recommendations, countries other than the US and Canada. Market research and public program data with a source URL and period on every figure; not a quote, not medical advice.

  ConnectorNo auth

• well_check_supplier_bank_detailsA

  WellA

  Check one bank account (IBAN) against what Well knows of one supplier: the supplier's known bank accounts, the day each first appeared, and the payments made to each. It draws no card. Use it when a person forwards new or changed bank details for a supplier ("our supplier changed bank", "nouveau RIB"), from a mail, an invoice or a typed message, before they pay. Pass the supplier's `company_id` and the IBAN as given; spaces and lower case are fine. The IBAN is compared exactly, across every currency pocket of the account. `status`: - `never_seen`: the supplier is known and none of its known accounts has this IBAN. - `already_paid_there`: the IBAN is a known account of the supplier and payments to it are on file. - `known_never_paid`: the IBAN is a known account of the supplier, with no payment to it on file. - `own_account`: the IBAN is one of the workspace's own accounts, not a supplier's. - `unknown_supplier`: the `company_id` names no company this workspace can read. Nothing is known about its accounts. - `invalid_iban`: the value is not a valid IBAN. Nothing was read. `checked_iban` gives the checked IBAN's first-seen day and payment count when the supplier has it. `accounts` lists every known account of the supplier by the last four characters of its IBAN, the checked one first: the day it first appeared (its first payment, or the day Well recorded it when that is earlier), the payment count, the totals per currency and the 10 most recent payments. `known_payment_count` is every payment to the supplier Well knows; a small number means a thin history, so say how many payments the answer rests on. `payments_without_known_account` counts payments to the supplier with no known account. `accounts_truncated: true` means the oldest accounts were not read; the checked IBAN is always read, so `never_seen` still holds. The check gives facts and never blocks a payment. Never call new bank details safe from this answer alone. When the token authorizes one workspace, call this directly — no workspace call is needed first. When it authorizes several, this read will not guess which one you mean: pass `workspace_id` on the call.

  ConnectorNo auth

• compare_local_pricesA

  Loa Healthcare PricingA

  U.S. care only, for users anywhere. For non-U.S. care, explain coverage without calling this tool or substituting U.S. prices. Compare hospitals near a ZIP by price or distance for a code from search_cpt_codes. Lead with answer: lowest cash, insurer comparison, verdict, follow-up, and search link. Its prices are single published prices; options use hospital medians. Without insurer, compare cash; with insurer, compare negotiated rates, not personal out-of-pocket costs. Preserve sources, dates, included fees, caveats, and each hospital’s city/state. Rank before limiting; missing matching prices are null and last. Do not send patient identifiers.

  ConnectorNo auth