"RStudio IDE" matching MCP tools:

• professionnels_in_radiusA

  france-data-mcpA

  Recherche de professionnels de santé libéraux conventionnés dans un rayon géographique. Précision géo HYBRIDE depuis le géocodage BAN (Chantier C) : ~77 % des PS sont géolocalisés à l'adresse précise (rue/bâtiment, `distance_km` exacte au m près), ~23 % restent au centroïde commune (~3 km, repli pour adresses non géocodables — DROM, Monaco, CEDEX, lieux-dits). Lire `geo_precision` PAR résultat — ne pas présumer une précision uniforme. Codes type_ps Ameli présents en base (3) : '1' médecins, '2' auxiliaires médicaux (fourre-tout : IDE, kinés, sages-femmes, podologues, orthophonistes, orthoptistes, IPA), '5' chirurgiens-dentistes. Pour cibler une profession précise (ex: IDE seuls, kinés seuls, podologues seuls), passer par `specialite_codes` plutôt que `type_ps_codes` qui ratisse plus large. Liste exhaustive des codes spécialité disponibles via le tool `lister_nomenclature(referentiel:'ameli_specialites')`. Multi-sites : par défaut un PS exerçant sur N adresses apparaît N fois — utiliser `dedupe_by_ps=true` pour regrouper par praticien et lister les sites en sous-objet. Distance retournée en km vol d'oiseau (haversine PostGIS) — pour distance routière, croiser avec un service externe (OSRM, ORS). Chaque PS géolocalisé porte `geo_precision` ∈ {`"adresse"`, `"centroide_commune"`} : `"adresse"` = coords BAN précises, `distance_km` exacte, classement individuel fiable ; `"centroide_commune"` = ~3 km, `distance_km` IDENTIQUE pour tous les PS d'une même commune (non discriminante intra-commune — filtre de zone uniquement, pas de classement/choix d'un PS individuel). **Param `precise_only`** (défaut false) : à true, exclut les PS au centroïde commune et ne renvoie que les ~77 % géocodés à l'adresse BAN (`distance_km` exacte) — recommandé pour les rayons courts (<3 km) et le classement intra-commune. PÉRIMÈTRE : libéraux conventionnés UNIQUEMENT. HORS PÉRIMÈTRE : médecins exclusivement hospitaliers/salariés, biologistes médicaux salariés en LBM, anatomopathologistes hospitaliers, médecins du travail, médecine légale. Pour effectifs tous statuts, voir Annuaire Santé ANS (RPPS, esante.gouv.fr) — non couvert par ce serveur. Source : Annuaire santé Ameli (Assurance Maladie), MAJ hebdomadaire. Réutilisation soumise à l'art. L.1461-2 CSP — citer la source et la date de sync.

  ConnectorNo auth

• professionnels_par_specialite_deptA

  france-data-mcpA

  Liste des professionnels de santé libéraux conventionnés d'un département, avec filtres optionnels par spécialité ou type de PS. Pour énumération administrative — pas de rayon. Codes type_ps Ameli présents en base (3) : '1' médecins, '2' auxiliaires médicaux (fourre-tout : IDE, kinés, sages-femmes, podologues, orthophonistes, orthoptistes, IPA), '5' chirurgiens-dentistes. Pour cibler une profession précise (ex: IDE seuls), passer par `specialite_code` plutôt que `type_ps_code` qui ratisse plus large. Liste exhaustive des codes spécialité disponibles via le tool `lister_nomenclature(referentiel:'ameli_specialites')`. Pagination : utiliser `offset` pour récupérer les pages suivantes quand `truncated=true`. Multi-sites : utiliser `dedupe_by_ps=true` pour regrouper par praticien. PÉRIMÈTRE : libéraux conventionnés UNIQUEMENT. HORS PÉRIMÈTRE : médecins exclusivement hospitaliers/salariés, biologistes médicaux salariés en LBM, anatomopathologistes hospitaliers, médecins du travail, médecine légale. Pour effectifs tous statuts, voir Annuaire Santé ANS (RPPS, esante.gouv.fr) — non couvert par ce serveur. Source : Annuaire santé Ameli (Assurance Maladie), MAJ hebdomadaire. Réutilisation soumise à l'art. L.1461-2 CSP — citer la source et la date de sync.

  ConnectorNo auth

• professionnels_rpps_par_deptA

  france-data-mcpA

  Liste tous les PS d'un département via RPPS (libéraux + salariés). Pour les libéraux conventionnés uniquement, préférer `professionnels_par_specialite_dept` (Ameli). Re-paginer via `offset` tant que `truncated=true`. Chaque résultat géolocalisé porte `geo_precision` ∈ {`"adresse"`, `"etablissement_finess"`, `"centroide_commune"`} — lire ce champ pour évaluer la fiabilité des `coords` (précise BAN/FINESS au m près vs centroïde commune ~3 km, non discriminant intra-commune). Filtres optionnels : `profession_code`, `savoir_faire_code`, `mode_exercice_code`. Catégorie par défaut : Civil (C, ~97 % — libéraux, salariés privés, hospitaliers contractuels). Opt-in : `include_agents_publics: true` ajoute Agents publics (M, ~0,3 % — PH titulaires, ARS, CNAM, Éducation nationale, PMI, militaires SSA) ; `include_etudiants: true` ajoute Étudiants (E, ~2,5 % — internes, externes, élèves IDE/SF). Réf : https://mos.esante.gouv.fr/NOS/TRE_R09-CategorieProfessionnelle/. ATTENTION nomenclatures : les codes ANS (`profession_code`, `savoir_faire_code`) sont une nomenclature DISTINCTE des codes Ameli (`specialite_code`, `type_ps_code`) — un même nombre désigne des choses différentes (ex: '10' = Médecin côté ANS, Neurochirurgien côté Ameli). Ne JAMAIS passer un code Ameli à un paramètre ANS : le filtre renverrait vide sans erreur. Découvrir les codes ANS via `lister_nomenclature(referentiel:'rpps_savoir_faire')`. Source : Annuaire Santé, Agence du Numérique en Santé (ANS) — Licence Ouverte v2.0

  ConnectorNo auth

• rpps_dans_etablissementA

  france-data-mcpA

  Liste les PS rattachés à un établissement FINESS (`num_finess` 9 chiffres). Pivot RPPS↔FINESS — répond à "qui travaille dans ce labo / hôpital / clinique ?". Le `mode_exercice` distingue les libéraux exerçant sur place (vacations) des salariés. Couverture : RPPS expose ce lien quand le PS l'a déclaré ; salariés CH/CHU/cliniques bien couverts. Sortie compacte : `coords` et `distance_km` sont `null` (le tool est par établissement, pas spatial — pour la géoloc, pivoter via `etablissement_by_finess` sur le `num_finess`). Catégorie par défaut : Civil (C, ~97 % — libéraux, salariés privés, hospitaliers contractuels). Opt-in : `include_agents_publics: true` ajoute Agents publics (M, ~0,3 % — PH titulaires, ARS, CNAM, Éducation nationale, PMI, militaires SSA) ; `include_etudiants: true` ajoute Étudiants (E, ~2,5 % — internes, externes, élèves IDE/SF). Réf : https://mos.esante.gouv.fr/NOS/TRE_R09-CategorieProfessionnelle/. Source : Annuaire Santé, Agence du Numérique en Santé (ANS) — Licence Ouverte v2.0

  ConnectorNo auth

• create_upload_urlA

  IBO Studio MCPA

  Get a short-lived presigned URL to upload one brand-asset file to IBO's private storage. Requires order_token from get_order; the storage location is bound to the order server-side. PUT the raw file bytes to url, then reference key in submit_brief files[]. Allowed: jpg png webp pdf svg mp4 mov zip ai psd; 250MB/file, 1GB per order.

  ConnectorNo auth

• save_turnA

  Vilix AIA

  Persist this exchange — fire-and-forget, never at the user's expense. Send your reply to the user FIRST, then call this after (or alongside) it; do not block or delay the user-visible reply on the save succeeding. `assistant_message` is the reply as actually sent, not a draft. If a save fails or you could not call it, retry once if your environment allows; otherwise catch up on the NEXT turn by also saving the missed prior turn. Re-sends are safe: retried or duplicate saves are deduplicated server-side (the response carries `deduped: true` and the original chat_id instead of double-saving). chat_id: omit or null to start a new conversation; otherwise reuse the id returned by a prior save_turn. source (required): the product or surface you run in — self-identify with a short label. Examples: Claude, Claude Code, Claude Cowork, Cursor, ChatGPT, Codex, Kiro, Gemini, a phone chatbot app, or an IDE agent. Use the same source for both messages in this turn. `attachment_context` (optional, default "") — if the user's message for this turn had an attachment (file, image, code paste, screenshot OCR), pass a short plain-text summary of it here. Persisted next to `user_message` so later retrieval can match on the attachment topic. Pass the SAME summary you passed to `get_context` this turn. Empty = no attachment. `turn_id` (optional) — a client-generated id for this turn (any short unique string). A retried save with the same turn_id never double-saves, even if the content was edited between attempts. Without it, identical re-sends are still deduplicated by content within a short window. `assistant_message_sha256` (optional) — sha256 hex digest of the assistant message as actually RENDERED to the user. If supplied, the server checks it against the stored message and returns `drift: true` when they differ (you saved a different message than the user saw). The save always proceeds; this is an integrity signal only.

  ConnectorOAuth

• aetherwave_upscale_imageA

  AetherWave StudioA

  Upscales a source image 2x or 4x. Pass a public `imageUrl` and an `upscaleFactor`. Flat 4 credits. Returns the upscaled 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

• aetherwave_generate_videoA

  AetherWave StudioA

  Generates a short-form video from a text prompt (T2V) or a text prompt + starting image (I2V). Submits, polls, and returns the final video URL. Default model is 'grok-imagine-t2v' (fast, 4 cr/s at 480p and 7 at 720p, with built-in KIE -> fal.ai fallback). Use list_video_models for the full lineup with credit cost per second. I2V models (e.g. 'grok-imagine-i2v', 'seedance-pro-i2v') require a public `imageUrl`. Video generation takes 1-8 minutes, so this tool almost always returns state "running" with a taskId: poll aetherwave_get_job with kind "video". ## Model selection guide for videos (when the user does not specify a model) Default: `grok-imagine-t2v` (4 cr/s at 480p, 7 at 720p, fast, has KIE -> fal.ai fallback for redundancy. Best general-purpose). Pick a different model when the prompt has these signals: - "highest quality" / "premium" / broadcast / commercial -> `veo3-quality` (Google VEO 3.1 Quality, fixed 350 cr for 8s, 3-5 min) - "fast premium" / quick high-quality -> `veo3-fast` (VEO 3.1 Fast, 84 cr fixed for 8s) or `veo3-lite` (42 cr) - Cinematic camera moves / dolly / pan -> `seedance-pro-t2v` (3-10 cr/s) or `kling-3.0-pro-t2v` (26 cr/s) - Realistic human motion / faces -> `hailuo-2.3-pro` (I2V, supply imageUrl) - Talking head / lip sync -> `kling-avatar-pro` (23 cr/s) or `infinitalk` (5-17 cr/s) - Anime / stylized / fantasy -> `wan-2-7-t2v` - NSFW / adult -> `wan-22-nsfw-i2v` (I2V only; auto-tags adult) - Animate this exact image -> any I2V variant (`grok-imagine-i2v`, `seedance-pro-i2v`, `hailuo-2.3-pro`) - First + last frame interpolation -> `seedance-pro-i2v` with both `imageUrl` + `endImageUrl` - Cheapest test -> `hailuo-2.0-standard` @ 512p (3 cr/s, ~18 cr for 6s) or `grok-imagine-t2v` @ 480p (4 cr/s, ~24 cr for 6s) - Clip 12-15s -> `grok-imagine-t2v` (accepts up to 15s) - True 4K -> `kling-3.0-4k-t2v` (94 cr/s, expensive but native 4K) **Audio in generated video:** `grok-imagine-t2v`, `seedance-pro-t2v`, and the VEO 3.x family include audio at base cost (no surcharge). Kling 2.6 and Kling 3.0 are the outliers - they price audio as a +50-100% surcharge (Kling 2.6 doubles the cost, Kling 3.0 Pro adds ~46%). Default to Grok / Seedance / VEO when sound matters and you don't want to think about audio pricing. **Cost framing:** resolution and duration drive cost more than model choice. A 6-second 480p Grok generation costs ~24 cr; the same prompt at 1080p Seedance 2 is ~858 cr (35x more). Pick the lowest acceptable resolution + duration first. **For I2V models:** `imageUrl` is required. For first+last-frame models, pass `endImageUrl` too. ## Consistent characters If the user names a person they already have ("my Amy character"), pass `character: "Amy"`: the tool attaches that character's reference pack and appends its `identityBlock` verbatim (or do it by hand: call `aetherwave_list_characters`, append `identityBlock`, pass `referenceImages`). Do NOT use `imageUrl` for this - a starting frame switches the engine to first-frame mode and drops the reference images, which is the opposite of what a consistent character needs. ## Writing dialogue `duration` is authoritative: the engine honours the seconds you ask for to within ~0.1s and then **fits the line to that length by changing pace**, rather than finishing early. So write the line to the clip length - do NOT estimate the clip length from the line. Measured on a 22-clip production: ~2 words per second of clip. A words-per-minute figure from a voice description describes the character, not the engine, and budgeting by it overran by 35%. Pass `generateAudio: true` for any clip with dialogue, and spell hard words the way they should be *spoken* ("super intelligence" rather than "superintelligence") - the engine reads the text literally and mangles unfamiliar compounds. ⚠️ A take can come back saying the WRONG WORDS and still report success. Re-rendering the identical prompt produced one clean take and one that dropped a whole sentence. For anything that will be assembled unattended, verify the rendered speech against the script before using the clip. Ask the user only when: - Single generation would cost more than 100 credits and they haven't confirmed - They asked for "the best" with no other signal; surface 2-3 options with cost ranges 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

• fvs_download_final_videoA

  Future Video StudioA

  Download a completed Future Video Studio final render URL to a local file. Use this only after fvs_get_render_status or fvs_get_paid_render_status returns a final_video_url for a completed render. The tool performs an unauthenticated HTTPS GET to that signed URL and writes the response bytes to output_path on the MCP server's local filesystem. It does not call the FVS Agent API, spend wallet credits, require FVS_AGENT_API_KEY, cancel jobs, or modify remote render state. Side effects and constraints: output_path is a local filesystem path for the MCP server process, parent directories are created, existing files are not replaced unless overwrite is true, and large videos may take minutes to download. The request timeout is 600 seconds. Use a fresh status check to refresh expired signed URLs, and do not pass arbitrary or untrusted URLs.

  Connector

  Destructive

  No auth

• list_skillsA

  Power Automate MCP Server by Flow StudioA

  Skill bundles: groups of the tools listed here that are used together for one task (diagnose-connection-references, build-flow, debug-flow, monitor-flow, discover, governance). Returns each bundle's name and one-line description. Use it when unsure which tools fit a request; tool_search "skill:<name>" returns the bundle's full guidance and definitions. Non-billable.

  ConnectorNo auth

• professionnels_rpps_in_radiusA

  france-data-mcpA

  Trouve les PS dans un rayon via RPPS (Annuaire Santé ANS — **tous statuts** : libéraux + salariés + mixtes + remplaçants ; vs `professionnels_in_radius` Ameli = libéraux conventionnés seuls). **Param critique `precise_only`** — Défaut `false` (mode hybride). À `true` : ne renvoie que les PS géolocalisés précisément (`distance_km` exacte au m près) — recommandé pour rayons courts (<3 km), classement intra-commune, "PS à <500 m d'une adresse". Chaque résultat porte `geo_precision` ∈ : - `"adresse"` — coords BAN rue/lieu-dit/bâtiment, `distance_km` exacte. - `"etablissement_finess"` — coords du site FINESS (via `num_finess`), `distance_km` exacte au site. - `"centroide_commune"` — centroïde commune (~3 km), `distance_km` IDENTIQUE pour tous les PS de la commune — ne PAS l'utiliser pour classer individuellement, seulement comme filtre de zone. Couverture actuelle : ~68,5 % précis, ~31,5 % `centroide_commune` résiduel. Mode hybride = précis (granularité adresse) + centroïde (granularité commune) fusionnés et triés globalement par `distance_km`. Filtres : `profession_codes` (ex: `["10"]` Médecin, `["60"]` Infirmier), `savoir_faire_codes` (spécialité fine DES/DESC), `mode_exercice_codes`. Codes mode_exercice ANS : L libéral, S salarié, M mixte, R remplaçant, B bénévole, A autre. Catégorie par défaut : Civil (C, ~97 % — libéraux, salariés privés, hospitaliers contractuels). Opt-in : `include_agents_publics: true` ajoute Agents publics (M, ~0,3 % — PH titulaires, ARS, CNAM, Éducation nationale, PMI, militaires SSA) ; `include_etudiants: true` ajoute Étudiants (E, ~2,5 % — internes, externes, élèves IDE/SF). Réf : https://mos.esante.gouv.fr/NOS/TRE_R09-CategorieProfessionnelle/. ATTENTION nomenclatures : les codes ANS (`profession_code`, `savoir_faire_code`) sont une nomenclature DISTINCTE des codes Ameli (`specialite_code`, `type_ps_code`) — un même nombre désigne des choses différentes (ex: '10' = Médecin côté ANS, Neurochirurgien côté Ameli). Ne JAMAIS passer un code Ameli à un paramètre ANS : le filtre renverrait vide sans erreur. Découvrir les codes ANS via `lister_nomenclature(referentiel:'rpps_savoir_faire')`. Source : Annuaire Santé, Agence du Numérique en Santé (ANS) — Licence Ouverte v2.0

  ConnectorNo auth

• upload_mediaA

  PickFuA

  Upload an image or video to get a permanent CDN URL for use in PickFu surveys. Three modes: (1) pass a publicly accessible HTTPS `url`; (2) pass base64 `data` (images only — JPEG/PNG/GIF/WebP/BMP/TIFF/SVG, max 20 MB; videos must use `url`) — ONLY when the file exists on local disk you can read directly (CLI/IDE clients such as Claude Code or Cursor); (3) call with neither `url` nor `data` to mint a PickFu-hosted upload session. If the user ATTACHED the file in the chat, always use mode 3: chat attachments are not reliably accessible as raw bytes, and re-encoding or compressing them into base64 tool calls fails on payload limits — do not attempt it. Present the returned `upload_url` to the user, wait for them to return, then call `check_upload` with the returned `token` to receive ordered `media-cdn.pickfu.com` URLs and continue the original task. YouTube/Vimeo/Wistia URLs do not need uploading.

  Connector

  Destructive

  OAuth

• style-purchase-options-by-idA

  Able.StyleA

  Find matching products and retailers where the user can buy a catalog style. Requires sign-in. Copy the exact catalog styleId from an earlier result; userStyle IDs are not supported. An explicit country overrides the saved account delivery country; otherwise the saved account country is preferred to the optional host country hint. Ask the user to select a country when neither is available. Save deliberate country selections with update-user-settings-tool using settings.deliveryCountry. Returns the complete options snapshot, including price, availability, retailer and product links. When searching or refreshing, call again with the same styleId and country to refresh. Buy links are obtained on demand with style-purchase-buy-url.

  ConnectorNo auth

• me.session_eventA

  AI Design BlueprintA

  Pro/Teams: append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the session reads as a system, not a transcript. CHANNEL PROVENANCE: this MCP channel posts the AGENT-SIDE vocabulary only. `steer` events and actor `human` are AIDB Studio-originated by contract (the owner posts them from the AIDB Studio session surface) and are REFUSED here, so a timeline entry can never impersonate the human side of the loop. Every event posted here is durably stamped with its channel. REQUIRES team mode: the session must have team_agents enabled (toggled in the web app on the session page); posting to a standalone session is refused so non-team sessions stay byte-identical. Owner-scoped: foreign session ids read as not found. event_type: handoff | pushback | plan_preview | gate | ack. actor: pm | engineer | designer | system. Read events back via me.sessions(session_id=...). WHEN TO CALL: at every role handoff (who -> who, what was passed), when a role pushes back on another's output, when the PM's plan is previewed for the co-planning gate, and when a hard gate blocks on an irreversible side-effect. ack: the IDE agent confirms it STARTED working on a steer. Post it FIRST on receiving a steer (summary like 'Started: <steer gist>'), then execute, then post handoff with the result. WHEN NOT TO CALL: not a chat log: post decisions and transitions, not every message; never to record a steer (steers arrive FROM the AIDB Studio via me.await_steer). REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page); 'This session has reached its event limit (500).' (the shared volume brake: start a new session for further team events); 'summary must not be blank.' (empty summaries are refused); steer/human posts are refused with a pointer to AIDB Studio. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• aetherwave_generate_imageA

  AetherWave StudioA

  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, 2 images per generation, 6 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'). ## Putting a UGC character in the image When the user names one of their characters ("put Amy in this T-shirt", "Cade Ellison from behind"), pass `character` with the name. The tool attaches that character's approved reference pack and identity text for you, and defaults the model to `gpt-image-2-t2i`. Put the product, garment or location in `referenceImages` as usual; describe the pose and framing in the prompt. Characters are the member's own creations, not third parties. Call `aetherwave_list_characters` if you need the names. ## Model selection guide (when the user does not specify a model) Default: `grok-imagine-t2i` (6 cr, 2 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), `nano-banana-2` (8 cr @ 1K), or `z-image-turbo` (2 cr, fastest) - "highest quality" / "premium" / no budget -> `gpt-image-2-t2i` at 2K (12 cr), or `grok-imagine-quality-t2i` (14 cr) - Text inside the image (signs, posters, typography) -> `gpt-image-2-t2i` (strongest lettering of the live models) - Album art / cover art -> `gpt-image-2-t2i` for one strong image; `grok-imagine-t2i` for 2 variations to choose from; `seedream-v4-t2i` if 4K wanted - Logo or design with embedded text -> `gpt-image-2-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` (2 outputs per call) or `seedream-v4-t2i` with `maxImages` up to 6 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, 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

• aetherwave_remove_backgroundA

  AetherWave StudioA

  Strips the background from an image, returning a PNG with transparent alpha. Pass a public `imageUrl`. Useful for product shots, character cutouts, logo isolation, or compositing onto a new background. ~5 credits per image. Recraft is the primary provider; on outage the tool auto-falls back to fal.ai BiRefNet v2 so single-image calls never silently fail. Works best on photographic subjects (people, products, animals); transparent-PNG inputs have no foreground to segment. 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

• aetherwave_upscale_videoA

  AetherWave StudioA

  Upscales a source video. Pass a public `videoUrl` and a target tier. Two engines: Atlas reaches 1080p and 2k only (7 and 10 cr/s; clips up to 53s at 1080p and 23s at 2k, source <=30fps); BytePlus also reaches 4k and 8k (4/8/16/62 cr/s at 1080p/2k/4k/8k) and is selected automatically for 4k and 8k. IMPORTANT, A TIER IS NOT A DIMENSION. These names are 16:9 standards, so '4k' means the 3840x2160 BOX and the source is fitted inside it, which means the SMALLER dimension wins. A square source at '4k' returns 2160x2160, NOT 3840x3840. Measured. A 3:4 source at Atlas '2k' returned 1664x2216. So never assume a tier lands on an exact pixel target: pick the highest sensible tier, then resize to exact dimensions in ffmpeg. Do NOT escalate to 8k to compensate, it is 62 cr/s to buy reconstruction a free lanczos resize gets you. For reference, Apple Music Album Motion Artwork requires exactly 3840x3840 and 2048x2732, and no tier produces either directly. Returns the upscaled video URL (R2-hosted). 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

• chieflab_approve_actionA

  ChiefLabA

  [chieflab_* alias of chiefmo_approve_action] Approve one ChiefMO publish/send action so its executor can fire. USE WHEN the user — in IDE chat — said 'approve <channel>' (e.g. 'approve linkedin', 'approve hn'), 'approve all', 'ship it', 'go ahead', or otherwise greenlit a specific draft you rendered. Match the user's words to the channel, look up agentGuide.renderInChat[channel].actionId from the launch response, and call this tool with that actionId. This is the IDE-native approval path — no need to push the user to the reviewUrl. Pass `actionId` (preferred) or `id` (legacy alias). P74: pass `autoExecute: true` AND the connector inputs (`platforms` for social / `recipients` + `subject` for email) to have the approval chain directly into execution — approve and ship in one tool call. Without autoExecute (or when connector is manual_handoff / blocked), the response includes executionPlan and the caller is expected to invoke the suggestedTool next.

  ConnectorNo auth

• chieflab_approve_actionA

  ChiefLabA

  [chieflab_* alias of chiefmo_approve_action] Approve one ChiefMO publish/send action so its executor can fire. USE WHEN the user — in IDE chat — said 'approve <channel>' (e.g. 'approve linkedin', 'approve hn'), 'approve all', 'ship it', 'go ahead', or otherwise greenlit a specific draft you rendered. Match the user's words to the channel, look up agentGuide.renderInChat[channel].actionId from the launch response, and call this tool with that actionId. This is the IDE-native approval path — no need to push the user to the reviewUrl. Pass `actionId` (preferred) or `id` (legacy alias). P74: pass `autoExecute: true` AND the connector inputs (`platforms` for social / `recipients` + `subject` for email) to have the approval chain directly into execution — approve and ship in one tool call. Without autoExecute (or when connector is manual_handoff / blocked), the response includes executionPlan and the caller is expected to invoke the suggestedTool next.

  ConnectorNo auth

• me.session_eventA

  AI Design Blueprint DoctrineA

  Pro/Teams: append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the session reads as a system, not a transcript. CHANNEL PROVENANCE: this MCP channel posts the AGENT-SIDE vocabulary only. `steer` events and actor `human` are AIDB Studio-originated by contract (the owner posts them from the AIDB Studio session surface) and are REFUSED here, so a timeline entry can never impersonate the human side of the loop. Every event posted here is durably stamped with its channel. REQUIRES team mode: the session must have team_agents enabled (toggled in the web app on the session page); posting to a standalone session is refused so non-team sessions stay byte-identical. Owner-scoped: foreign session ids read as not found. event_type: handoff | pushback | plan_preview | gate | ack. actor: pm | engineer | designer | system. Read events back via me.sessions(session_id=...). WHEN TO CALL: at every role handoff (who -> who, what was passed), when a role pushes back on another's output, when the PM's plan is previewed for the co-planning gate, and when a hard gate blocks on an irreversible side-effect. ack: the IDE agent confirms it STARTED working on a steer. Post it FIRST on receiving a steer (summary like 'Started: <steer gist>'), then execute, then post handoff with the result. WHEN NOT TO CALL: not a chat log: post decisions and transitions, not every message; never to record a steer (steers arrive FROM the AIDB Studio via me.await_steer). REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page); 'This session has reached its event limit (500).' (the shared volume brake: start a new session for further team events); 'summary must not be blank.' (empty summaries are refused); steer/human posts are refused with a pointer to AIDB Studio. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• connect_accountA

  Dreambooth StudioA

  Connect this conversation to the person's Dreambooth Studio account. The answer's status says what happened. already_connected: an account is connected; nothing to do. awaiting_approval: it returns a link the person opens in their own browser to sign in with Google and approve. A Google account with the same email as an existing Dreambooth account connects that account. Ask them to open it and say when they are done; do not call this tool again while waiting. use_client_sign_in: this client connects accounts through its own app or connector settings, where they can sign in with an email and password or with Google, so no link is returned. Ask them to connect Dreambooth there (the client also asks by itself when a tool needs an account), then repeat their question. Either way, someone who has no Dreambooth account yet gets one when they sign in. Call this when another tool reports that no account is connected, or when someone asks to connect or switch accounts.

  ConnectorNo auth