"How to create UI components with NativeWind for React Native" matching MCP tools:

• get_design_guidelinesA

  Marmo UI MCPA

  MANDATORY FIRST CALL before writing any @marmoui/ui code in this session. Returns a step-by-step generation checklist (which tools to call, in what order), critical rules (no namespace sub-components, PageSection is self-closing, no Sidebar export), component patterns, and ICON LIBRARY RULES. Pass iconLibrary (default "phosphor"; also "material" | "lucide" | "tabler" | "heroicons" | "feather") to get that library's import source, icon name map, and weight/style mapping — and pass the SAME value to review_generated_code so it enforces it. Ask the user which icon library they want before writing UI code. Call topic="patterns" to get the generation checklist specifically.

  ConnectorNo auth

• get_design_guidelinesA

  marmo-uiA

  MANDATORY FIRST CALL before writing any @marmoui/ui code in this session. Returns a step-by-step generation checklist (which tools to call, in what order), critical rules (no namespace sub-components, PageSection is self-closing, no Sidebar export), component patterns, and ICON LIBRARY RULES. Pass iconLibrary (default "phosphor"; also "material" | "lucide" | "tabler" | "heroicons" | "feather") to get that library's import source, icon name map, and weight/style mapping — and pass the SAME value to review_generated_code so it enforces it. Ask the user which icon library they want before writing UI code. Call topic="patterns" to get the generation checklist specifically.

  ConnectorNo auth

• scaffold_providerA

  UploadkitA

  Return a ready-to-paste snippet that wraps the Next.js root layout with `<UploadKitProvider>` so React components can talk to the upload route handler. When to use: right after scaffold_route_handler, to complete the wiring. The snippet goes in `app/layout.tsx`. Without the provider, UploadKit React components throw at runtime. Returns: a plain-text string containing a short explanatory note followed by a fenced tsx code block. Takes no parameters — the endpoint path is always `/api/uploadkit` since that is what scaffold_route_handler produces. Read-only, deterministic, idempotent.

  ConnectorNo auth

• screen.observeA

  GlasswarpA

  Read the current screen: UIA targets (numbered ids + native coords) and a text summary. Does not move mouse/keyboard. Default image=false (no JPEG) for speed; set image=true only when you must judge pixels visually (then max_width≈960, quality≈60). If changed=false, JPEG is omitted even when requested — do not re-analyze; wait or act differently. If dirty is null, assume changed. Prefer input.send_actions for multi-step UI; observe after meaningful steps, not after every click. Target ids are valid only until the next UI change.

  ConnectorNo auth

• build_get_examplesA

  SuperoB

  Fetch a COMPLETE, production-quality reference app (schemas.py + config.py + setup.py + ui/app.js) to copy patterns from — the single biggest lever for app quality. archetype='index' (default) lists the available archetypes with per-file byte sizes; pick the one closest to your app ('commerce-marketplace' | 'service-booking' | 'ops-dashboard' | 'multitenant-portal' | 'saas-billing') and fetch it BEFORE authoring your UI. These are real 'stunning' apps; mirror how they compose the SDK components, art-direct the landing page, and structure schemas. Optional file= to fetch just one file ('schemas.py' | 'config.py' | 'setup.py' | 'ui/app.js'). Responses are PAGED (~32KB/section): when the header says more:true, fetch the next section with offset=<next_offset> — never re-fetch from 0.

  ConnectorNo auth

• contrast_checkA

  rnv-color-mcpA

  WCAG contrast ratio between a foreground and background color, for accessibility. Both accept a hex, CSS name, RNV brand name, or saved-palette reference. Returns the ratio (1.0-21.0) plus pass/fail for AA and AAA at normal and large text sizes and for UI components. Read-only and deterministic, with no side effects. Use this for legibility and accessibility checks; to measure raw perceptual difference between two colors rather than readability use color_difference instead.

  ConnectorNo auth

• migrate_to_propelauth_frontendA

  PropelAuth Integration MCP ServerA

  Returns instructions for migrating to PropelAuth in a frontend framework such as React, JavaScript, TypeScript, or when using Next.js for just the frontend (e.g. client-side rendered). Guidance includes migrating from several auth providers, such as Clerk or Auth0. Each guidance will include documentation from the auth provider and PropelAuth. It is important to follow the instructions carefully to ensure a successful integration. Make sure to use the 'Installation' guidance first. It is important to call every guidance to ensure a successful integration. Do not update a component/hook/etc from the auth provider until you receive guidance about that component/hook/etc. CRITICAL: If the current implementation uses a traditional OAuth/OIDC flow (e.g., via express-openid-connect, passport-auth0, or similar backend-managed session libraries), you MUST select 'OAuth' as the framework, regardless of the frontend library (React/Vue/etc.). Only select 'React' or 'Javascript' if the current implementation uses a frontend-only SDK (like @auth0/auth0-react) or if using fullstack Next.js.

  ConnectorNo auth

• contrast_checkA

  rnv-color-mcpA

  WCAG contrast ratio between a foreground and background color, for accessibility. Both accept a hex, CSS name, RNV brand name, or saved-palette reference. Returns the ratio (1.0-21.0) plus pass/fail for AA and AAA at normal and large text sizes and for UI components. Read-only and deterministic, with no side effects. Use this for legibility and accessibility checks; to measure raw perceptual difference between two colors rather than readability use color_difference instead.

  ConnectorNo auth

• read_schematicA

  boardrepoA

  Use when the user asks how a public board is wired, what a component (e.g. U1) connects to, or which pins are on a net (e.g. GND), in that design. Returns the board's latest geometry-free connectivity. No focus returns a bounded overview (components + a net index); ref returns one component and the nets it connects to with the other pins on those nets; net returns the pins on that net. These are in-design connections, not an authoritative manufacturer pinout, and a very large design may be truncated (the response flags this). Prefer a focused ref or net over repeated overviews. Use get_bom for purchasing and read_file for raw source. If nets are still computing, continue with the components shown and try again shortly rather than inferring connectivity.

  ConnectorOAuth

• list_header_componentsA

  RoutebaseA

  List the header components defined at one level: 'spec' (needs specId) or 'project'. Set includeUsageCounts to see how often each is referenced — spec level only. Returns the ids and rowVersions needed to change them or assign them in a header policy. Requires project context. Use this for spec or project level; for the organization level use list_org_header_components.

  ConnectorAPI key

• write_filesA

  KleapA

  Write WHOLE files DIRECTLY — YOUR model generates the code, Kleap stores, builds and deploys it as-is. To change something in a file that ALREADY EXISTS, use edit_files instead (read_files → edit_files): it replaces just the lines you name, while write_files makes you retype the entire file and silently drops whatever you leave out — on a 30KB shared layout that is how headers and footers get wiped. No Kleap-AI step, so what ships is byte-for-byte what you wrote — the right choice when a phrase, a URL or a schema must be exact. Publishing still audits the result (see publish_app). Best for scaffolding exact pages/components — e.g. programmatic-SEO routes. Astro paths (src/pages/*.astro, src/data/*.json, src/components/*.astro, public/*). Overwrites by path. NPM PACKAGES: do not write package.json (the build replaces it) — the build installs whatever your code IMPORTS, so `import { jsPDF } from "jspdf";` is all it takes. Supported on import: @tiptap/*, jspdf, pdf-lib, html2canvas, papaparse, file-saver, jszip, @ffmpeg/*, howler, wavesurfer.js, browser-image-compression, react-dropzone, recharts, chart.js, d3, @tanstack/*, react-hook-form, three, @react-three/*, leaflet, maplibre-gl, gsap, framer-motion, zustand, date-fns, react-markdown, axios, socket.io-client, radix-ui/*, next-themes, lucide-react, @tabler/*, openai, @ai-sdk/*; anything else is refused at build with a message naming it. A client-side router is never the answer — a route is a FILE (src/pages/about.astro → /about). IMAGES AND BINARIES: set encoding:"base64" on the file and send the bytes — that is how you put a logo, a photo, an OG image, a favicon or a font on the site (png/jpg/webp/svg/ico/mp4/woff2/pdf, 512KB max each decoded). Without it you can only write text, and a site with no images looks unfinished. To ADD an image from a text prompt WITHOUT sending any bytes (a real photo's base64 is too big to emit reliably), use generate_image — Kleap generates it and stores it for you. To REMOVE a page or asset, use delete_files — overwriting it with empty content leaves a URL that answers 200 with nothing, which is worse than a 404. DATA & ACCOUNTS: write_files only STORES files — it cannot provision the Kleap Database, so DB or auth code pushed here has no backend and silently does nothing. Stand the feature up with modify_app first, then edit those pages here. After writing, call publish_app to build & go live.

  Connector

  Destructive

  OAuth

• write_filesA

  KleapA

  Write WHOLE files DIRECTLY — YOUR model generates the code, Kleap stores, builds and deploys it as-is. To change something in a file that ALREADY EXISTS, use edit_files instead (read_files → edit_files): it replaces just the lines you name, while write_files makes you retype the entire file and silently drops whatever you leave out — on a 30KB shared layout that is how headers and footers get wiped. No Kleap-AI step, so what ships is byte-for-byte what you wrote — the right choice when a phrase, a URL or a schema must be exact. Publishing still audits the result (see publish_app). Best for scaffolding exact pages/components — e.g. programmatic-SEO routes. Astro paths (src/pages/*.astro, src/data/*.json, src/components/*.astro, public/*). Overwrites by path. NPM PACKAGES: do not write package.json (the build replaces it) — the build installs whatever your code IMPORTS, so `import { jsPDF } from "jspdf";` is all it takes. Supported on import: @tiptap/*, jspdf, pdf-lib, html2canvas, papaparse, file-saver, jszip, @ffmpeg/*, howler, wavesurfer.js, browser-image-compression, react-dropzone, recharts, chart.js, d3, @tanstack/*, react-hook-form, three, @react-three/*, leaflet, maplibre-gl, gsap, framer-motion, zustand, date-fns, react-markdown, axios, socket.io-client, radix-ui/*, next-themes, lucide-react, @tabler/*, openai, @ai-sdk/*; anything else is refused at build with a message naming it. A client-side router is never the answer — a route is a FILE (src/pages/about.astro → /about). IMAGES AND BINARIES: set encoding:"base64" on the file and send the bytes — that is how you put a logo, a photo, an OG image, a favicon or a font on the site (png/jpg/webp/svg/ico/mp4/woff2/pdf, 512KB max each decoded). Without it you can only write text, and a site with no images looks unfinished. To ADD an image from a text prompt WITHOUT sending any bytes (a real photo's base64 is too big to emit reliably), use generate_image — Kleap generates it and stores it for you. To REMOVE a page or asset, use delete_files — overwriting it with empty content leaves a URL that answers 200 with nothing, which is worse than a 404. DATA & ACCOUNTS: write_files only STORES files — it cannot provision the Kleap Database, so DB or auth code pushed here has no backend and silently does nothing. Stand the feature up with modify_app first, then edit those pages here. After writing, call publish_app to build & go live.

  Connector

  Destructive

  No auth

• list_wizard_campaignsA

  Metadata MCP ConnectorA

  List wizard (Metadata-native) campaigns for the current account with pagination, sorting, and experiment-status filtering. KEYWORDS: campaigns, list, browse, wizard, native, all campaigns, campaign list, launched campaigns, paused campaigns, active campaigns USE THIS TOOL WHEN THE USER ASKS: - "Show me all campaigns" / "List campaigns" / "What campaigns do we have?" - "Show active campaigns" / "List paused campaigns" / "Show completed campaigns" - "Show recent campaigns" / "Last N campaigns" - "Campaigns sorted by spend / leads / CPL / created date" - Page-by-page campaign browsing for the campaigns UI DO NOT USE if the user: - Wants details on ONE SPECIFIC campaign by name → use search_campaigns_by_names - Wants budget group info (not campaigns) → use list_budget_groups / get_budget_group - Wants per-experiment performance → use experiment_performance_stats / search_experiments TWO INDEPENDENT FILTERS (COMBINE TO MATCH UI TABS): 1) status — filters by CAMPAIGN status. Accepts a comma-separated subset of: Draft, Launched, Finished. - Draft: the campaign exists but has never been launched. - Launched: the campaign has been launched (experiments may be Active, Paused, or idle). - Finished: the campaign has reached its end date. - Omit to include all three. 2) experiment_statuses — filters by EXPERIMENT status inside each campaign. Accepts a comma-separated subset of: Active, WithoutSpend, Paused, Completed, Failed. Omit to include all five. HOW TO MIX THEM (mirrors the UI tabs on /campaigns): - "All" tab: omit both → API returns everything. - "Active" tab: status="Launched", experiment_statuses="Active,WithoutSpend" (launched campaigns with live or not-yet-spending experiments). - "Paused" tab: status="Launched", experiment_statuses="Paused" (launched campaigns whose experiments are paused). - "Draft" tab: status="Draft" (campaign hasn't been launched yet — experiment status doesn't apply). - "Finished" tab: status="Finished". SORTING: - sort_by: createdDate (default), startDate, endDate, name, budget, spent, leads, cpl, cpc, ctr, impressions, clicks, status - sort_order: asc | desc (default: desc) PAGINATION: - page: 0-based page index (default 0) - size: results per page (default 25; the UI campaign list fetches 25–50) RESPONSE SHAPE: { "totalElements": 435, "totalPages": 18, "data": [ { "id": 173290, "accountId": 1455, "name": "2026_Q2_NA_Builder_Content_...", "createdDate": "2026-01-15T12:00:00Z", "visibility": "VISIBLE" | "ARCHIVED", "budget": 25, "startDate": "...", "endDate": "...", "status": "Launched" | "Draft" | ..., "activeExperiments": 9, "pausedExperiments": 0, "totalExperiments": 9, "leads": 0, "spent": 0, "impressions": 48, "clicks": 0, "cpc": 0, "cpl": 0, "ctr": 0.0, "goal": "CTR" | "CPL", "campaignGroup": "TOF - AO - Social - Billing - BA", "tags": [...] }, ... ] } WORKFLOW (UI-style): list_wizard_campaigns(page=0, size=25) → render list → user clicks campaign → search_campaigns_by_names / get_campaign_by_wizard_id for details.

  ConnectorAPI key

• create_appA

  CharmingA

  Create a new interactive web app and render it inline. Use this to build a new app from a request. Existing-contract apps return after publication. Eligible authors can select the ESM manifest schema with an idempotency_key to accept a background build; that result contains a buildId to poll with get_app_build, and has no app URL before publication. If `module` reuses a `manifest.id` the caller already owns, the new app replaces the existing app module, UI, and styles in place; use update_app to edit a known app ID by UUID. Apps persist state through a backend `env.storage` (Workers KV) binding and call backend operations from the frontend via `window.charming.api`. The `module`, `ui`, and `description` parameter docs carry the authoring rules — including the fill-viewport outer-container rule on `ui`; the charming:app-guide prompt has the full guide and a canonical example. Read the public docs without a browser using read_docs({ path: "build-mcp.md" }); read_docs({}) lists available pages. If a request needs in-app AI calls, external integrations, native apps, scheduled jobs, SQL, notifications, or view-only sharing, do not fake support. Build the closest local-state version, then log the gap with `submit_feedback`. The charming:app-guide prompt has alternatives. The charming:design-guide prompt documents Charming's default visual style for generated `ui` (single accent, warm neutrals, real type hierarchy; no gradients or decorative emoji) — a default that yields to any user-requested aesthetic. When telling the user where to open or share the app, always give them `shareUrl` from the result — never the `url` field, which is machine-only and embeds a write-capable access token.

  Connector

  Destructive

  OAuth

• token_flowsA

  NansenA

  Get hourly token-flow history for ONE holder segment over a date range. Use `token_recent_flows_summary` instead for an on-chain snapshot across ALL wallet categories. **Note:** Using `holder_segment: smart_money` is not a good proxy for an overall market view. Use it only if user explicitly requests it, or to combine it with other non smart money data. This is a **more granular** tool than `token_recent_flows_summary` and provides the TOTAL flows over the entire time frame broken down by segment. **Modes:** - `onchain_tokens` (default): Analyze on-chain tokens by contract address - `perps`: Analyze Hyperliquid perpetual futures by symbol (chain auto-set to "hyperliquid") — supports native tokens **NOTE:** Native tokens (0xeee…, So111…) cannot be queried in `onchain_tokens` mode. If a native placeholder address is supplied, this tool returns Hyperliquid perpetual-futures flows for that chain's native coin instead (e.g. hyperevm → HYPE, bnb → BNB, base → ETH) and prepends a prominent data-source warning. For native-token wallet-category flows on-chain, use `token_recent_flows_summary`.

  ConnectorNo auth

• token_flowsA

  NansenA

  Get hourly token-flow history for ONE holder segment over a date range. Use `token_recent_flows_summary` instead for an on-chain snapshot across ALL wallet categories. **Note:** Using `holder_segment: smart_money` is not a good proxy for an overall market view. Use it only if user explicitly requests it, or to combine it with other non smart money data. This is a **more granular** tool than `token_recent_flows_summary` and provides the TOTAL flows over the entire time frame broken down by segment. **Modes:** - `onchain_tokens` (default): Analyze on-chain tokens by contract address - `perps`: Analyze Hyperliquid perpetual futures by symbol (chain auto-set to "hyperliquid") — supports native tokens **NOTE:** Native tokens (0xeee…, So111…) cannot be queried in `onchain_tokens` mode. If a native placeholder address is supplied, this tool returns Hyperliquid perpetual-futures flows for that chain's native coin instead (e.g. hyperevm → HYPE, bnb → BNB, base → ETH) and prepends a prominent data-source warning. For native-token wallet-category flows on-chain, use `token_recent_flows_summary`.

  ConnectorNo auth

• get_project_infoA

  FracteraA

  Project reference / help desk about Fractera. Use this to answer ANY user question about what Fractera is, how it works, its architecture, components, modes, data ownership, pricing, use cases, partner program, etc. — especially while a deploy is running and the user wants to learn more. TOKEN-ECONOMY: call with NO arguments first to get the lightweight list of section ids+titles, then call again with a single `section` id to fetch just that section. NEVER try to fetch everything at once; pull only the section(s) relevant to the user question. Set `lang:"ru"` for Russian-speaking users.

  ConnectorNo auth

• get_project_infoA

  FracteraA

  Project reference / help desk about Fractera. Use this to answer ANY user question about what Fractera is, how it works, its architecture, components, modes, data ownership, pricing, use cases, partner program, etc. — especially while a deploy is running and the user wants to learn more. TOKEN-ECONOMY: call with NO arguments first to get the lightweight list of section ids+titles, then call again with a single `section` id to fetch just that section. NEVER try to fetch everything at once; pull only the section(s) relevant to the user question. Set `lang:"ru"` for Russian-speaking users.

  ConnectorNo auth

• search_docsA

  RoxyAPI Docs MCP Server (keyless, for coding agents)A

  Search the RoxyAPI knowledge base and get back ranked documentation snippets, each with a source URL. It covers API endpoints with their request and response fields, SDK usage for TypeScript, Python, PHP, C#, and Go, the WordPress plugin, authentication and API keys, UI components, and step by step integration guides. Call this first whenever you need to integrate RoxyAPI into an app: to find which endpoint or SDK method to use, what parameters a call takes, how to authenticate, or how to wire a feature end to end. Pass the user question verbatim as `query`. If the first results miss, rephrase once and retry.

  ConnectorNo auth

• create_webhook_endpointA

  Reach MCPA

  Register a URL to be called when something happens on LinkedIn, so an agent or an n8n/Make workflow can react instead of polling. Returns the signing secret ONCE; deliveries carry 'Reach-Signature: t=<unix>,v1=<hex HMAC-SHA256(secret, t + '.' + body)>'. Events: message.received, connection.new, account.status_changed, quota.threshold_reached, quota.reached, or '*' for all. Omit account_ids to subscribe for every account of the user. https only. Use when the user wants to react to a reply, a new connection, a quota alert or a job event from n8n, Make or their own code; needs an https URL they control. Not for the model to call itself.

  ConnectorAPI key

• create_g2_intent_linkedin_native_dynamic_audienceA

  Metadata MCP ConnectorA

  Create a **G2 Intent - LinkedIn Native (Dynamic)** audience (platform `customAudienceType=DYNAMIC_G2`). AUDIENCE TYPE (mirrors the UI's "Audience Type" dropdown): • UI label: "G2 Intent - LinkedIn Native (Dynamic)" • Platform enum: DYNAMIC_G2 • Refreshes daily as G2 intent signals update; targets LinkedIn natively. PREREQUISITE: • Both G2 and LinkedIn integrations MUST be connected. If either is missing, do NOT call this tool — recommend `create_firmographic_audience` instead. WHEN TO USE (exact user phrasing this tool should match): • "G2 Intent - LinkedIn Native (Dynamic)" • "G2 LinkedIn Native Dynamic" • "LinkedIn native G2 intent audience" • The user explicitly mentions BOTH G2 intent AND LinkedIn native targeting. WHEN NOT TO USE: • If the user asked for "G2 Intent (Dynamic)" without "LinkedIn Native" → use `create_g2_intent_dynamic_audience`. • If the user asked for "G2 Intent (Static)" → use `create_g2_intent_static_audience`. BUYING STAGES — REQUIRED BY THE PLATFORM: The platform UI marks Buying Stages as required. If the user did not name any stages, STOP and ask the user which of AWARENESS / CONSIDERATION / DECISION to target. DO NOT silently default — that produced wrong audiences in PRD-29702 / PRD-29703. CRITERIA (LinkedIn-native shapes; free-text fields are resolved server-side via the LinkedIn references API): • employees — LinkedIn-native employee ranges. Valid labels: see the schema (e.g. "201-500", "501-1000", "1001-5000"). • revenues — LinkedIn-native revenue ranges (e.g. "$1M-$10M", "$10M-$100M"). • company_names — free-text company names (resolved to LinkedIn company IDs). • location_country_ids — country IDs (e.g. 229=US, 228=UK). • job_titles — free-text titles (resolved to LinkedIn job-title IDs). • skills — free-text professional skills (resolved to LinkedIn skill IDs). PARAMETERS: • name (required, ≤ 50 chars) • intent_days (required, 1-365) • buying_stages (REQUIRED by platform — ask the user if missing; do NOT default) • employees, revenues, company_names, location_country_ids, job_titles, skills (all optional) RETURNS: id, audience_id, audience_name, audience_type (DYNAMIC_G2), status, buying_stages, intent_days, expectedNumberOfCompanies, expectedNumberOfContacts.

  ConnectorAPI key