"Android Studio" matching MCP tools:

• generate_image

  NotFair-MetaAds

  Generate one image from a prompt using OpenAI GPT Image 2. Returns a public URL you can embed in markdown or pass to a creative-asset tool (e.g. Google Ads `createImageAsset`). Counts against the user's monthly quota. Prompt craft (GPT Image 2 rewards long, specific, instruction-style prompts — write a paragraph, not keywords): - Lead with the medium: photograph, 3D render, isometric vector, watercolor, flat illustration, studio product shot. Single biggest quality lever. - Then specify subject, setting, mood, color palette, lighting (e.g. 'golden hour, soft backlight'), and camera/perspective (close-up, wide, overhead, low angle, macro). - Keep the focal subject in the center 80% of the frame — ad platforms crop edges across placements. - Prefer lifestyle / in-context scenes over isolated-on-white product shots. Google explicitly recommends 'physical settings with organic shadows and lighting' for ad creative. - Don't render text unless the user asks for specific copy. Overlaid text is often unreadable at small ad sizes and Google flags it as a quality issue. - Avoid negative prompts ('no X, no Y'). GPT Image often pulls the rejected concept in — describe what you want instead. Ad-policy rules to bake into prompts: - No collages, borders, watermarks, mirrored / skewed / over-filtered looks. - No fake UI elements (play buttons, download/close icons) — Google Ads policy violation. - Don't overlay a logo on the photo; logos belong inside the scene (on a product, sign, storefront). - Blank space should be under 80% of the frame — the subject is the focus. Aspect ratios — match the target placement: - Google Ads asset slots: '1.91:1' landscape (required), '1:1' square (required), '4:5' portrait, '9:16' vertical (Demand Gen / Shorts). - Meta / social: '1:1' or '4:5' feed; '9:16' stories/reels; '1.91:1' link previews. - Hero / web banners: '16:9' or '3:2'. Default is '1:1'. Quality vs latency: 'low' ~5s drafts; 'medium' balanced; 'high' runs the four-stage Understand/Plan/Generate/Review pipeline (30–50× slower than low) — use only for production-final fidelity. Output format: default 'png' (lossless). Use 'webp' or 'jpeg' for smaller photographic assets. background='transparent' requires png/webp (use for logos, cutouts, UI assets).

  Connector

• estimate_generation_cost

  Cannon Studio

  Estimate credits for a Cannon Studio generation request before creating billable work. Requires OAuth or a developer API key; it may update key/token usage metadata but does not spend credits, enqueue jobs, or change assets. Use get_api_operation first if operation or input fields are unclear, then pass the same operation/input pair to create_generation_request after user approval.

  Connector

• create_generation_request

  Cannon Studio

  Create billable async Cannon Studio generation work only after explicit user approval. Requires OAuth or a developer API key; can spend credits up to max_credits and cannot be cancelled through MCP after submission. Use estimate_generation_cost first, then set confirmed=true and a user-approved max_credits cap. This tool does not create API keys, charge payment methods directly, or delete assets.

  Connector

• get_checkout_link

  Cannon Studio

  Return the first-party Cannon Studio checkout or inquiry URL for a selected offering. Public read-only: no auth, no state changes, no charges; use list_offerings first to get a valid product_key.

  Connector

• tool_search

  Power Automate MCP Server by Flow Studio

  PREFER THIS over guessing tool names when picking from this server. Searches Flow Studio MCP tools by keyword, skill bundle, or explicit selector and returns full JSON schemas for matched tools so they can be called immediately. Call this whenever the user request maps to functionality you are not 100% sure about, OR when you want to load a whole skill bundle (build-flow, debug-flow, monitor-flow, discover, governance) at once. Query forms: (1) "skill:<name>" — fetch the full bundle (use list_skills first to see options); (2) "select:name1,name2" — fetch exact tools by name; (3) free-text keywords like "cancel run" or "trigger url" — ranked match against tool name + description. Non-billable.

  Connector

• epub_to_audiobook

  Sats4AI - Bitcoin-Powered AI Tools

  Convert books (EPUB/PDF/TXT) to full audiobooks with automatic chapter detection, multi-voice narration, and optional translation to any language before narration. 3 voice tiers: OmniVoice Global (602+ langs, 100 chars/sat), Inworld Premium (#1 ranked TTS ELO 1217, 50 chars/sat), Minimax Studio (voice cloning from reference clip, 10 chars/sat). Min 500 sats. Async — returns jobId, poll until completed (5-60+ min). Single payment, full outcome — no multi-step orchestration required. Pay with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='epub_to_audiobook'.

  Connector

• search_within

  Studio Ghibli

  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

• buy_studio

  moltdj

  Buy a Studio subscription for $25 USDC (30 days). Requires authentication. This endpoint returns HTTP 402 with x402 payment instructions. Your x402-enabled HTTP client will handle the USDC payment automatically. After payment, you get Studio tier: 20 tracks/day, 5 episodes/week, video, audience insights, and more.

  Connector

• get_contact_info

  Symbols of Wealth Studio

  Returns contact information for Symbols of Wealth Studio — email, website, location, and how to engage. Use this when a user wants to actually reach out to or hire Symbols of Wealth Studio, rather than browse the full studio profile.

  Connector

• generate_image

  NotFair-GoogleAds

  Generate one image from a prompt using OpenAI GPT Image 2. Returns a public URL you can embed in markdown or pass to a creative-asset tool (e.g. Google Ads `createImageAsset`). Counts against the user's monthly quota. Prompt craft (GPT Image 2 rewards long, specific, instruction-style prompts — write a paragraph, not keywords): - Lead with the medium: photograph, 3D render, isometric vector, watercolor, flat illustration, studio product shot. Single biggest quality lever. - Then specify subject, setting, mood, color palette, lighting (e.g. 'golden hour, soft backlight'), and camera/perspective (close-up, wide, overhead, low angle, macro). - Keep the focal subject in the center 80% of the frame — ad platforms crop edges across placements. - Prefer lifestyle / in-context scenes over isolated-on-white product shots. Google explicitly recommends 'physical settings with organic shadows and lighting' for ad creative. - Don't render text unless the user asks for specific copy. Overlaid text is often unreadable at small ad sizes and Google flags it as a quality issue. - Avoid negative prompts ('no X, no Y'). GPT Image often pulls the rejected concept in — describe what you want instead. Ad-policy rules to bake into prompts: - No collages, borders, watermarks, mirrored / skewed / over-filtered looks. - No fake UI elements (play buttons, download/close icons) — Google Ads policy violation. - Don't overlay a logo on the photo; logos belong inside the scene (on a product, sign, storefront). - Blank space should be under 80% of the frame — the subject is the focus. Aspect ratios — match the target placement: - Google Ads asset slots: '1.91:1' landscape (required), '1:1' square (required), '4:5' portrait, '9:16' vertical (Demand Gen / Shorts). - Meta / social: '1:1' or '4:5' feed; '9:16' stories/reels; '1.91:1' link previews. - Hero / web banners: '16:9' or '3:2'. Default is '1:1'. Quality vs latency: 'low' ~5s drafts; 'medium' balanced; 'high' runs the four-stage Understand/Plan/Generate/Review pipeline (30–50× slower than low) — use only for production-final fidelity. Output format: default 'png' (lossless). Use 'webp' or 'jpeg' for smaller photographic assets. background='transparent' requires png/webp (use for logos, cutouts, UI assets).

  Connector

• cabgo_create_trial

  Cabgo Builder

  Public (no auth): create a Cabgo tenant in TRIAL state — **no payment required up-front**. Returns companyId + activationUrl + welcome email confirmation. **NEW**: pass `presetId` (taxi_classic | delivery_food | delivery_gas) to bootstrap branding + services + zones + tariffs + module toggles in the SAME call — no need to call apply_preset separately. Pass `triggerBuild:'android'` to also queue an APK in the same call. **Cash-only is the default**: the tenant lands with cashEnabled=true, so if the operator only wants to operate in cash they don't need to call cabgo_configure_payment_provider at all. Trial duration: 14 days. **Required**: ownerEmail (use whatever the operator already gave you in chat — don't re-ask), companyName.

  Connector

• open_in_studio

  kernelcad

  Persist the current kernelCAD model and return a one-click link that opens it in the kernelCAD Studio web app, where the user can view and share it. Pass the full `.kcad` source you have been building as `code`. The result includes a `slug` — pass that `slug` on every subsequent call to UPDATE the same project in place: the user's open Studio tab re-renders live, so they can watch the model evolve as you iterate. Omit `slug` only for a new, separate model (each omission creates a new project and link). Call this when the user says "open it in Studio", "let me see it", "show me the model", after you finish a build, and after each meaningful revision while iterating.

  Connector

• polymarket_arbitrage

  Studio Ghibli

  REQUIRES one of `event` (single-event mode) OR `topic` (cross-event mode) — call with no args fails. Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. `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}.

  Connector

• capture_animation

  kernelcad

  Capture a kernelCAD script's animationView({...}) timeline to an MP4 (ffmpeg) or a PNG frame sequence, verifying the sampled poses for part interference. FILE ONLY: pass { file } (a .kcad.ts path) — there is no { code } mode, because the capture engine renders from a file on disk (its relative lib.fromSTEP imports resolve against the script directory). MP4 by default; pass { frames_dir } to write frame-0000.png... and skip ffmpeg entirely (mutually exclusive with output_path). Animation-pose interference verification runs by default (keyframe times + segment midpoints) BEFORE any browser/ffmpeg cost; { no_verify: true } skips it and { verify_every: n } additionally samples every n-th frame time. Pass { focus } or { hide } (arrays of feature ids or assembly part names, mutually exclusive) to isolate parts in the rendered frames — same semantics as `kernelcad render --focus/--hide`; visibility is render-only and does NOT affect the pose verification. Collisions DO NOT fail the call — the artifact is still written as evidence with ok: true; read verified: false + the collisions[] array. ENVIRONMENT REQUIREMENT (identical to `kernelcad render`): capture drives a headless browser against a running studio dev server reachable at http://localhost:5173 (or the VITE_PORT override); there is no bundled-static serving mode yet, so the same dev-server precondition applies in a production MCP install. Returns { ok, output_path, frame_count, duration_ms, fps, verified, verify_skipped?, collisions: [{ t_ms, a, b, volume_mm3 }], diagnostics }.

  Connector

• cabgo_create_my_app

  Cabgo Builder

  Materializes a free Cabgo workspace for the operator and queues an Android build of their branded app. No payment, no card, no checkout — the workspace is free to create and operate. Call ONLY when the user explicitly wants to create / launch / spin up / set up a new app for their business — verbs like 'create', 'launch', 'build me', 'set up an app for'. Do NOT call this for setup / installation / connector questions (use cabgo_install_instructions). Ask the user 2 things: (1) what type of business — taxi / food delivery / gas distribution? (2) what brand name for their app? Optionally city + brand color. **The connected OAuth user becomes the owner automatically** — no email or name is needed in the body. **A single user can own multiple tenants** — calling this again creates a NEW workspace rather than erroring. Branding tweaks happen via other Cabgo tools after creation. Any plan / billing / subscription management is done by the operator on https://www.cabgo.app — never through this tool.

  Connector

• list_services

  Parallax Ventures

  List Parallax’s services with real pricing. Filter by track: "ai" (done-for-you AI agent teams), "music" (Parallax Records / Baba Studio production), or "all".

  Connector

• get_contact_info

  symbols-of-wealth-studio

  Returns contact information for Symbols of Wealth Studio — email, website, location, and how to engage. Use this when a user wants to actually reach out to or hire Symbols of Wealth Studio, rather than browse the full studio profile.

  Connector

• ask_pipeworx_grounded

  Studio Ghibli

  Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 3,683 across 865 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

• list_pending_community_events

  socialloop-mcp

  List events awaiting approval in a community you run — who submitted, when, and whether they asked for your community payout. Returns a studio link to review + approve (approval routes money, so it's done in the studio, not chat); use reject_community_event to decline. Requires community_id. Read-only.

  Connector

• get_my_active_references

  switch

  Read the user's active reference strip in Switch Studio — the typed slots (face, body, outfit, scenery, product, general) the user fills with reference images before generating. Returns the count, per-type breakdown, and the refs themselves with their type labels and URLs. Call this BEFORE generate_image whenever the user says "use my refs", "use my reference images", references images they prepared in Studio, or wants to generate from a scene they already laid out. The strip is the bridge: pictures the user drops into Studio land here, and Studio's own generations read from here. Pass the returned URLs into generate_image's reference_image_urls so the same refs anchor the result.

  Connector