Skip to main content
Glama
626,187 tools. Updated 2026-10-01 04:58

"Turbo" matching MCP tools:

  • Generate an AI video with H3 Max Turbo (default: renders in seconds, 5-15 s), Grok Imagine, Seedance, Veo, or Kling. Every account gets its first H3 Max Turbo clip at 5 s / 480p free; after that it costs credits like any other preset. Users can name a model family naturally: H3, Hailuo or MiniMax map to H3 Max Turbo, Veo to Veo 3.1 Fast, Kling to Kling 2.5 Turbo, Grok to Grok Imagine, Seedance to Seedance 2.0 Mini, and Seedance Pro to Seedance 1.5 Pro. Never omit model when the user named one. Call list_models or quote_generation first when the user wants to review models and costs before spending credits.
    Connector
    Destructive
    OAuth
  • Render a video from a text prompt using ViewMax Studio. Returns immediately with a job id; the clip is not ready yet. Rendering takes roughly two to four minutes. Call `get_video` with the returned id to collect the result, waiting about 15 seconds between checks. Do not poll faster than that, and tell the user it is rendering rather than going silent while you wait. Credits are charged to the account the API key belongs to, and refunded automatically if the render fails. Available models: - seedance-2-mini: Native audio and multi-shot cuts in one clip. Longest takes we offer. (4–15s, 480p/720p/1080p, with audio) - h3-max: Native 768p with no upscale pass. Fastest turnaround, up to 15s takes. (5–15s, 480p/768p, with audio) - h3-max-turbo: Half the price of H3 Max at the same sizes, and the quickest render we carry. (5–15s, 480p/768p, with audio) - viewmax-agent-2.0: Writes, cuts and scores a whole video from one brief, at any length you ask for. (15s and up, 720p, with audio) Leave `model` unset to use the default. Call `list_video_models` if you need exact per-model limits or prices.
    ConnectorNo auth
  • Generates one or more images from a text prompt (T2I) or a text prompt + reference image(s) (I2I). Submits the job, polls until terminal, and returns the final image URLs. Default model is 'grok-imagine-t2i' (fast, 6 images per generation, 5 credits). Use list_image_models to see the full lineup with pricing. For I2I, pass `referenceImages` as an array of public image URLs and pick a model with I2I support (e.g. 'grok-imagine-i2i', 'wan-2.5-spicy-i2i'). ## Model selection guide (when the user does not specify a model) Default: `grok-imagine-t2i` (5 cr, 6 outputs per call, fast, general purpose). **Strong recommendation: when a single high-quality output is what's wanted** (most agent / one-shot workflows), prefer `gpt-image-2-t2i` (9 cr @ 1K / higher @ 2K, single deterministic image, best general quality across realism, illustration, typography, and composition; supports up to 2K resolution and most aspect ratios including auto). This is the front-runner for serious creative output where you don't need to pick from 6 variations. Pick a different model when the prompt has these signals: - "single best result" / "one image" / production / no time to pick from variations -> `gpt-image-2-t2i` (9 cr, 1 output, top general quality) - "photoreal" / "photo of" / "realistic" -> `gpt-image-2-t2i` (9 cr, best general realism) or `imagen-4` (12 cr, very high quality) or `z-image-turbo` (2 cr, fastest) - "highest quality" / "premium" / no budget -> `gpt-image-2-t2i` at 2K, or `grok-imagine-quality-t2i` (16 cr @ 1K, 22 cr @ 2K), or `imagen-4-ultra` - Text inside the image (signs, posters, typography) -> `ideogram-v3-t2i` (best in class) or `gpt-image-2-t2i` (also strong) - Artistic / painterly / stylized -> `midjourney-t2i` - Album art / cover art -> `gpt-image-2-t2i` for one strong image; `grok-imagine-t2i` for 6 variations to choose from; `seedream-v4-t2i` if 4K wanted - Logo or design with embedded text -> `ideogram-v3-t2i` - NSFW / adult / explicit -> `wan-2.5-spicy-t2i` (auto-tags creation as 18+; routes to adult gallery) - Cheapest possible / quick test -> `z-image-turbo` (2 cr) - Multiple variations to compare -> keep `grok-imagine-t2i` (6 outputs default) or use `numImages` on a multi-output model For I2I (reference image provided): prefer the dedicated `aetherwave_edit_image` tool for "change something in this image" intent. Use `aetherwave_generate_image` with I2I models only when you specifically want style transfer (`midjourney-i2i`), premium quality (`grok-imagine-quality-i2i`), or adult content (`wan-2.5-spicy-i2i`). Always pass an explicit `aspectRatio` (e.g. "1:1" for square album art, "16:9" for video thumbnails, "9:16" for shorts/reels). Some upstream providers reject submissions with no aspect ratio. Ask the user only when: - The prompt contradicts itself (e.g., "highest quality but cheapest") - The user requested "the best model" with no context, surface 2-3 options with tradeoffs - A single generation would cost more than 20 credits and the user has not confirmed Returns within ~45 s. If the result has state "running" the job is still rendering: poll aetherwave_get_job with the returned taskId and kind every ~10 s. Pass wait:true ONLY if your MCP client permits tool calls longer than 60 s (most do not). Pass async:true to get the taskId back immediately without waiting.
    ConnectorNo auth
  • Live Solana priority-fee oracle: current microLamports/CU percentiles and recommended low/medium/high/turbo tiers. Call before sending any Solana transaction.
    ConnectorNo auth
  • Generate a short video with Kling 2.5 Turbo Pro — smooth, cinematic motion. Returns a link to the finished video. THE SLOWEST TOOL HERE: usually ~90 seconds, sometimes longer, and some clients give up before it returns. BEFORE calling, tell the user it will take a minute and a half; if they need something faster, generate_video_veo is about 60s. If the call appears to fail or time out, say so plainly — do NOT silently retry, since the video may well have been generated and a retry bills them again.
    ConnectorOAuth
  • Audit a project's dependencies in one shot. Returns a single-sentence `verdict` (e.g. "DO NOT INSTALL — 1 hallucinated: fastapi-turbo") that an agent can paste into its reply, plus per-package health/vulns/recommendation. Detects hallucinated packages, deprecated, typosquats, critical vulnerabilities. Accepts EITHER {ecosystem, packages:[name@ver, …]} (up to 100, returns JSON) OR {packages:[{ecosystem, package}, …]} (up to 50, mixed ecosystems, returns text brief). USE WHEN: user pastes package.json/requirements.txt/Cargo.toml; agent generated install command; 'is my stack OK'. RETURNS: JSON with `verdict`, `project_risk`, `summary.hallucinated_packages`, `summary.deprecated_packages`, per-package health.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Composite MCP server for Things 3 on macOS that bundles multiple read calls into single requests, enables batch writes, and provides a self-healing read path to handle TCC protection issues.
    8
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Provides a complete agency operating system with 20+ roles (strategy, creative, marketing, etc.) accessible via MCP and includes a Pixel Office visualizer for interactive simulation.
    3
    2
    PolyForm Noncommercial 1.0.0
  • Set CONTEXT tags on one completed activity (full-array write; empty array clears). Tags describe how the session should be READ, not what it contained: workout (a plain training session — read it against the plan), heat (hot conditions — HR inflated, output depressed, expected), altitude (ridden high — hypoxic shift, lower power is normal), indoor (turbo trainer, treadmill or a virtual platform — still air means HR climbs through the session at unchanged power, so drift is expected and is not a fitness signal; speed, distance and pace are the platform's invention, so judge power, HR and RPE and never km or min/km, and never compare them with outdoor numbers), race (max effort by design — grade vs the race goal, not the plan), test (FTP/lactate/field test — peak efforts deliberate; consider estimate_thresholds after), group (group ride — surging, structure deviations expected), commute (transport volume, not training intent). Use when the athlete tells you the context ('вчера была жара', 'это была гонка') or when you infer it and they confirm. Immediate write — the tag chips appear on the activity card.
    ConnectorOAuth
  • Reframes an image to a new aspect ratio by intelligently outpainting the edges. Pass a public `imageUrl` and the target `aspectRatio` ('16:9', '9:16', '1:1', '4:3', '3:4', etc.). Three speed tiers: 'turbo' (5 cr, fast), 'balanced' (10 cr, default), 'quality' (14 cr, slowest, best edges). Returns the reframed image URL. Returns within ~45 s. If the result has state "running" the job is still rendering: poll aetherwave_get_job with the returned taskId and kind every ~10 s. Pass wait:true ONLY if your MCP client permits tool calls longer than 60 s (most do not). Pass async:true to get the taskId back immediately without waiting.
    ConnectorNo auth
  • Check whether an AI model identifier is deprecated, retiring, or has silently changed (price, context window, capabilities). Accepts any spelling a provider or SDK uses, e.g. 'gpt-4-turbo', 'azure/gpt-4.1-mini', 'claude-opus-4-1-20250805'. Call this before writing a model identifier into code.
    ConnectorNo auth
  • Transcribes an audio file with Whisper large v3 turbo: pass an https URL (mp3, wav, flac, m4a, ogg, up to 10 MB) or base64 audio in a POST. Returns the text, the detected language with its probability, the duration, and timed segments; add words=true for word-level timestamps. Around 100 languages. You are only charged if the transcript is delivered. No API key, no account. $0.02 per call, paid over x402 (USDC).
    ConnectorNo auth
  • Search 1.8M+ Brazilian vehicle listings aggregated from 96 platforms (OLX, Webmotors, Napista, etc.). Returns listings with price, year, mileage, location, source platform, the original ad URL, FIPE reference price and a deal_score (% vs FIPE; negative means priced below FIPE). Tips for best results: - Free-text `query` matches the listing TITLE only (e.g. "Onix LTZ turbo"). - For exact brand/model/version filtering, resolve names to ids first with list_brands / list_models / list_versions and pass brand_id/model_id/ version_id — it is faster and more accurate than the text fields. - `location` is a 2-letter UF (e.g. "SP") or a city name. - `sort_by="newest"` (default) lists the most recently LISTED cars first — the date a listing first appeared on its source, not when we last saw it. - `sort_by="best_deal"` ranks by lowest price-to-FIPE ratio. - `per_page` is capped at 50. Use `page` (1-20) to paginate; past the first 20 pages, narrow the search with filters. `total_count` and `total_pages` are returned.
    ConnectorNo auth
  • Search 1.8M+ Brazilian vehicle listings aggregated from 96 platforms (OLX, Webmotors, Napista, etc.). Returns listings with price, year, mileage, location, source platform, the original ad URL, FIPE reference price and a deal_score (% vs FIPE; negative means priced below FIPE). Tips for best results: - Free-text `query` matches the listing TITLE only (e.g. "Onix LTZ turbo"). - For exact brand/model/version filtering, resolve names to ids first with list_brands / list_models / list_versions and pass brand_id/model_id/ version_id — it is faster and more accurate than the text fields. - `location` is a 2-letter UF (e.g. "SP") or a city name. - `sort_by="newest"` (default) lists the most recently LISTED cars first — the date a listing first appeared on its source, not when we last saw it. - `sort_by="best_deal"` ranks by lowest price-to-FIPE ratio. - `per_page` is capped at 50. Use `page` (1-20) to paginate; past the first 20 pages, narrow the search with filters. `total_count` and `total_pages` are returned.
    ConnectorNo auth
  • Clone a voice you own or have permission to use, from a single audio sample. Returns a reusable voice_id for text_to_speech. Requires consent=true; cloning a voice to impersonate someone is prohibited. High-fidelity reproduction capturing tone, cadence, and accent. SAMPLE REQUIREMENTS: MP3, M4A or WAV, 10 seconds to 5 minutes, 20 MB max, one speaker, no background music — a sample outside these limits is rejected upstream and the clone fails. Turbo (faster) or HD (higher quality) modes. 7,500 sats per clone. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='clone_voice'.
    ConnectorNo auth
  • Compare four image models on the same useful brief. Run makes four paid images. Judge exact text, object count, composition and color before choosing the model for your own task. Each contender alr… text:Shared test brief -> image:Contender 1 -> image:Contender 2 -> image:Contender 3 -> image:Contender 4; returns image (muse-image/text-to-image, 1:1) + image (turbo, 1k) + image (grok-imagine-image/v2.0/text-to-image, 1:1) + image (recraft-v4, 1024×1024) saved to disk (file paths in result). Runs on NanoGPT — $0.59 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.2455, ~1m 39s. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#image-model-arena). The same bicycle-repair poster brief sent to four image models. All four retained the requested text in this run; only Grok rendered recognizable tire levers. Compare all outputs before choosing.
    ConnectorNo auth
  • Text-to-speech voiceover MP3 (ElevenLabs Turbo 2.5, 32 languages, up to 1000 chars). ~$0.05.
    ConnectorNo auth
  • Text-to-speech voiceover MP3 (ElevenLabs Turbo 2.5, 32 languages, up to 1000 chars). ~$0.05.
    ConnectorNo auth
  • Record ONE thing you now know about the athlete, with how long it is true. This is the assistant's memory: it is NOT a copy of the snapshot and NOT a training log. Three tests, all must pass — (1) it is not already handed to you every turn (age, weight, hours, available days, thresholds, zones, race dates, the plan, load, readiness, response_profile), (2) no tool computes it (get_metric_history, get_records, get_activity), (3) it outlives this session — the verdict on one workout goes on that workout with set_activity_notes. AREA decides what survives when context is tight: "health" and "constraint" are never cut, "pattern" is the only capped area. Nuance goes in `tags`, which are free. CONSTRAINTS include a fixed commitment on a day the profile calls free, another coach's remit, an injury to plan around, and EQUIPMENT — tagged `equipment`, recorded as what they actually own in their words, with a horizon like anything else (a gym membership is an `until`, a turbo in the hallway is often a `season`). HORIZON is required and there is no "unknown": if you cannot say how long it holds, ASK before writing. "stands" = until they say otherwise. "until" + dueDate = it ends (a race, an arrangement); when the date passes the fact stops applying and its opposite does NOT start applying. "recheck" + dueDate = it does not become false, it becomes untrustworthy (a threshold, a blood value, weekly hours). "season" + seasonFrom/seasonTo = true only part of the year (months, may wrap: 11-03 is November to March). "pattern" = an observation; set confirmations as you see it again. `dueAction` is the line between a date that becomes a CALENDAR item and a date that is merely a question. Set it only when the due date carries something the athlete DOES ("сдать ферритин", "перемерить порог 30-мин тестом") — that is proposed as a calendar entry on the date itself. Leave it empty for "ask whether this still holds": no calendar clutter for a conversation. Silent when the athlete just told you the fact. A CARD when it carries a dueAction (it will put something in their calendar), when it is a pattern (that is your inference about them, not their words), or when it `replaces` a fact already on their page. ONE IDEA, ONE LINE. If a live fact of the same area already says something like this, the call is HELD and you get those facts back with their ids: answer with `new:true` (genuinely different — both stay, and a different day, date, trip or measurement IS different however alike the wording), `replaces:<id>` (this supersedes it — the old one is retired as this is written), or `confirms:<id>` (literally the same thing — that fact is bumped and your line is discarded). Every fact in your snapshot already ends with its #id, so a pattern you see again is confirm_fact on that id, not a second add_fact.
    ConnectorOAuth
  • Render your SVG through Picorn with real typography and declarative image workers. Put placeholder <rect> elements inside the SVG and choose their backend with data-clipart-engine="svg-converter" (fresh ComfyUI image, background removal, then Picorn PNG→SVG vectorisation), data-clipart-engine="z-image-turbo" (raster photo/cutout), or data-clipart-engine="library" (existing vector only). Include data-clipart-prompt; use data-clipart-num-colors="1..7" for svg-converter, and data-clipart-keep-bg="true" for a full scene. Picorn resolves all placeholders internally; never call the admin converter or return generated base64 yourself. Returns an inline preview and public creationUrl.
    ConnectorNo auth
  • Use Picorn's native editor engine: first generate raster artwork with self-hosted Z-Image Turbo on ComfyUI, remove its background, then convert it through the bundled multi-colour SVG converter. Generates five variants, selects the strongest result and returns the top three. Signets also return one layered editor file that displays the three shortlisted SVGs inside the same native project. Use this tool for every newly generated signet and custom icon.
    ConnectorNo auth
  • Generate a raw image with self-hosted Z-Image Turbo. Returns an inline preview and public creationUrl.
    ConnectorNo auth