"Server for MCP Protocol with On-Screen UI Interaction" matching MCP tools:

• get_protocol_tvlA

  TeardropA

  Get Total Value Locked for one or many DeFi protocols from DeFiLlama: current USD TVL, 7/30-day change, fees and revenue when reported, per-chain breakdown, and optional daily historical series. Batch multiple protocols via protocols=[...] — batch responses return one compact economic summary per protocol; single-protocol calls add chain and historical detail. Supports 3,000+ protocols; use DeFiLlama slugs ('aave-v3', 'uniswap-v3'); common aliases are auto-corrected. Use when: Use for protocol-level economic questions — size, growth, fees, or revenue of a specific protocol. For 2+ protocols always batch in one call rather than calling per-protocol. Pass include_historical=true with days when a trend is needed; without it the response is a current TVL scalar. For ecosystem-level chain comparisons use get_chain_metrics instead. Limitations: Third-party DeFiLlama analytics, not on-chain truth. Upstream revenue failures surface as revenue_error_type and null economic fields are data gaps — never fabricate values for them. Alternatives: get_chain_metrics, get_yield_rates, get_dex_volume

  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

• defi_protocolsA

  MCPFax Macro & Market IntelligenceA

  Rank DeFi protocols by total value locked from DefiLlama, filtered by chain, category or name substring, with each protocol's slug, category, chain list, TVL in USD, 1d/7d TVL change and market cap. Use it to size a protocol, find the biggest venues on a chain, or resolve the slug the protocol-detail tool needs. A protocol DefiLlama publishes no TVL for keeps a null figure, never a zero. Read live at request time and held for 5 minutes. Costs $0.008 USDC per call via x402 on Base; an unpaid call returns the payment challenge instead of data, and a call that returns no data is never settled so it costs nothing. Equivalent HTTP route: GET /defi/protocols.

  ConnectorNo auth

• get_protocol_tvlA

  teardropA

  Get Total Value Locked for one or many DeFi protocols from DeFiLlama: current USD TVL, 7/30-day change, fees and revenue when reported, per-chain breakdown, and optional daily historical series. Batch multiple protocols via protocols=[...] — batch responses return one compact economic summary per protocol; single-protocol calls add chain and historical detail. Supports 3,000+ protocols; use DeFiLlama slugs ('aave-v3', 'uniswap-v3'); common aliases are auto-corrected. Use when: Use for protocol-level economic questions — size, growth, fees, or revenue of a specific protocol. For 2+ protocols always batch in one call rather than calling per-protocol. Pass include_historical=true with days when a trend is needed; without it the response is a current TVL scalar. For ecosystem-level chain comparisons use get_chain_metrics instead. Limitations: Third-party DeFiLlama analytics, not on-chain truth. Upstream revenue failures surface as revenue_error_type and null economic fields are data gaps — never fabricate values for them. Alternatives: get_chain_metrics, get_yield_rates, get_dex_volume

  ConnectorNo auth

• get_wallet_historyA

  TeardropA

  Get one page of decoded transaction history for an EVM wallet across DeBank-supported chains. Returns send, receive, and approval categories with protocol, token, exchange, gas, and USD metadata. Use the returned next_cursor as start_time to page backward. Use when: Use for wallet activity discovery, protocol interaction history, exchange exposure, and gas analysis. Page backward with next_cursor for older activity. Use get_transaction or decode_transaction when one known transaction needs block-level details. Limitations: DeBank returns at most 20 entries per call and the data may be stale. This tool is not a complete ledger, PnL engine, or cost-basis calculator because historical execution prices and all transfer semantics are not guaranteed. Alternatives: get_transaction, decode_transaction

  ConnectorNo auth

• get_wallet_historyA

  teardropA

  Get one page of decoded transaction history for an EVM wallet across DeBank-supported chains. Returns send, receive, and approval categories with protocol, token, exchange, gas, and USD metadata. Use the returned next_cursor as start_time to page backward. Use when: Use for wallet activity discovery, protocol interaction history, exchange exposure, and gas analysis. Page backward with next_cursor for older activity. Use get_transaction or decode_transaction when one known transaction needs block-level details. Limitations: DeBank returns at most 20 entries per call and the data may be stale. This tool is not a complete ledger, PnL engine, or cost-basis calculator because historical execution prices and all transfer semantics are not guaranteed. Alternatives: get_transaction, decode_transaction

  ConnectorNo auth

• list_my_merchantsA

  JobMojitoA

  FALLBACK merchant list for clients WITHOUT UI support. Do NOT use this to choose or switch merchants when a UI is available — call `jobmojito_configuration` instead (it renders an interactive picker), and do not hand-format a merchant list as text. Use this tool only when the client cannot render MCP App UI. Returns the user's own account plus any sub-merchants; after a pick, pass `merchant_id=<chosen id>` on subsequent calls (OMIT for the own account).

  ConnectorNo auth

• ios_page_sourceA

  Robot Actions — Remote Device ControlA

  Get the UI hierarchy (page source) of an iOS device — THE single source of truth for element coordinates (physical screen points). Default format is "description": a compact list of visible named elements as `Type: "name" @ (cx,cy) WxH`, where (cx,cy) is the element CENTER and the exact tap point; when the visible text differs from the name (an app that sets accessibility identifiers) it is appended as label="…", and the element holding focus is flagged [focused] — on an Apple TV that is the element tvos_select/tvos_focus acts on. Prefer acting on these labels via ios_tap_by_label rather than tapping raw coordinates. Elements with 0-width/height bounds (e.g. bottom-tab labels) are flagged [zero-area] — they cannot be tapped by coordinate; use ios_tap_by_label instead. FINDING THINGS IN LONG LISTS: pass `search` to grep the WHOLE hierarchy (including elements scrolled off-screen) — matches below the fold are flagged [off-screen]; bring them into view with ios_scroll_to_element, don't swipe blindly. To disambiguate duplicate labels, filter by `type` or use ios_find_element (strategy "accessibility id"). Use format "xml" to JUDGE FROM THE TREE instead of trusting a coordinate: with `label` it returns the COMPLETE SUBTREE of that element (a sign-in dialog is ~15 lines, where the whole tree is ~185k characters and will not fit in a response), and without it the tree comes back with anonymous layout containers pruned — nothing findable is ever hidden behind a pruned ancestor. Reach for the subtree whenever you need attributes the compact format omits: value, placeholderValue, focused, enabled. Requires an active iOS automation session (auto-starts if needed).

  ConnectorOAuth

• ios_tap_by_labelA

  Robot Actions — Remote Device ControlA

  PREFERRED way to tap on iOS: find a UI element by its accessibility label and tap it in one call via the automation session. No coordinate math, and it works on zero-area elements (e.g. bottom-tab labels) where ios_tap(x,y) would miss. Use this before falling back to ios_tap with raw coordinates. If the element is off-screen it auto-scrolls to bring it into view first (disable with autoScroll:false). On no match, returns similar labels (incl. off-screen) to retry with. If neither the accessibility tree nor auto-scroll finds it, it falls back to reading the screen with OCR and taps the matching on-screen text; the reply says when OCR was used. Requires an active iOS automation session (auto-starts if needed). On a device set to direct-input-only it needs no session: it scrolls the element into view, reads the visible text on the screen to find where it is, taps there, and reports `changed` (whether the screen changed afterwards). That path needs the label to be visible text; an icon-only control fails fast, so use input:"session" for those.

  ConnectorOAuth

• ios_safari_close_tabA

  Robot Actions — Remote Device ControlA

  Close Safari tabs on an iOS device by title, or list what is open. Safari's tab overview is the only way to close a tab — the Web Inspector protocol behind ios_safari_list_pages cannot do it — so this drives the native UI. Call with no title to list the open tabs and close nothing. Titles match case-insensitively on any part of the title. Note this sees MORE tabs than ios_safari_list_pages, which only reports pages that are loaded and inspectable. Requires Safari in the foreground and an active iOS automation session.

  ConnectorOAuth

• find_agentsA

  Remnant Read — Agent Experience & EvidenceA

  Find public agents by capability, skill, domain or declared protocol when choosing a collaborator. Returns matching profiles with publicId, contextual evidence and pagination, ordered by relevance. Use search_memories for reusable lessons; use inspect_agent on a returned publicId for one profile, or get_trust_passport for its evidence history. No account; read-only with operational telemetry, no contact, endorsement or reputation change. Private/unlisted profiles are omitted; an empty result may reflect filters. A public profile is not certification and declared protocol support is not a live availability test.

  ConnectorNo auth

• resolve_pending_replyA

  Dayze — Life ContextB

  Pending Replies: mark a reply done: sent (default; the user replied, logged privately in the contact's history) or dismissed. Dayze sends nothing. By reply_id, or person_name / person_id when that person has exactly one unsent reply (otherwise the candidates come back and nothing changes). Marking sent writes one private interaction for the linked contact (not for an unlinked reply, and not twice); interaction in the result says what was written. Reopen with update_pending_reply status pending. Requires API key or OAuth with context.write. ($0.05; API key required)

  ConnectorNo auth

• add_screensA

  PagefullyA

  Adds screens of the app for pages to be drawn from: captures of the running app, beside the screenshots its App Store listing already has. Use it when the listing's screenshots are stale, when a page needs a screen the listing does not show, or when the app is not on the store yet. Returns each screen with its position, which is what edit_page takes as "screen". A page made after this may choose an uploaded screen by itself. Nothing is sent to Apple. How to capture one: run the app in the iOS simulator, go to the screen, then run: xcrun simctl io booted screenshot --type=jpeg home.jpg (leave out --type=jpeg for a PNG). Use a simulator whose screen is a size Apple takes for a screenshot: iPhone 17 Pro Max or 16 Pro Max (1320 x 2868), or iPad Pro 13-inch (2064 x 2752). Capture real screens with real content, with no debug overlay. How to send it. If you have a shell, upload the file itself, which is the quickest way and keeps the picture out of this conversation: curl -X POST -H "Authorization: Bearer $PAGEFULLY_TOKEN" -F "file=@home.jpg" https://pagefully.com/api/v1/apps/APP_ID/screens (the token is the one this server was given; never print it). Otherwise call this tool with each screen as "url", an https address of the file on the public internet that the server fetches (no redirect is followed), or as "data", the file in base64, which only suits a small JPEG. PNG or JPEG, 8 MB a file at most, 10 in one call. An app has 10 places for iPhone screens and 10 for iPad, the listing's own included. Called with no screens it lists the app's screens and what is accepted. Tell the person which screens were added, and never upload a picture that is not a screen of their own app.

  ConnectorNo auth

• create_widget_metricA

  ActivitySmithA

  Create a Lock Screen Widget metric: a named value, such as monthly revenue or deploy success rate, that the user can show in an ActivitySmith widget on their iPhone or iPad Lock Screen. Create each metric once, then send values with set_widget_metric_value using the same key. To change the label or format later, use update_widget_metric. The new metric has no value yet, and nothing changes on the Lock Screen until the user adds a widget for it. Fails if the key already exists in the account. Returns the created metric, including its public_id.

  ConnectorOAuth

• recommend_iconsA

  SupericonsA

  Recommend a coherent icon set for up to 20 named UI slots in one call. Uses task context to narrow ambiguous meanings. When context is insufficient, returns needs_clarification with labeled interpretation options instead of guessing. Invalid inputs and service failures return a plain-language reason and a next step instead of a bare protocol error. Returns one recommendation and optional alternatives for each resolved slot, with explicit public library labels and visual preview URLs where available. Library key si means Supericons, not Simple Icons.

  ConnectorNo auth

• get_lending_ratesA

  TeardropA

  Get current on-chain lending supply/borrow APYs for Aave v3 reserves and Compound v3 markets on Ethereum or Base, with per-asset snapshots and Compound utilization. Use for protocol-specific yield comparisons such as USDC on Aave vs Compound. Use when: Use for protocol-specific lending-rate questions (e.g. 'Aave vs Compound USDC rates'). Prefer over get_yield_rates when the protocols are known; use get_yield_rates for broad pool discovery across many protocols. Do not fall back to web_search when this returns errors — report them. Limitations: On-chain snapshots of Aave v3 and Compound v3 on Ethereum and Base only; not a multi-protocol yield aggregator. Rates are point-in-time and change per block. Returns an errors list — report each unavailable protocol explicitly and treat empty rates with empty errors as transient RPC unavailability. Alternatives: get_yield_rates, get_defi_positions, get_liquidation_risk

  ConnectorNo auth

• get_yield_ratesA

  TeardropA

  Get DeFi yield pool rates from DeFiLlama across 1,000+ protocols and all chains: pools sorted by APY with TVL, base/reward APY, and 7d/30d mean APY context, filterable by protocol, chain, min TVL, min/max APY, and symbol. Returns up to 50 pools. For protocol-specific lending comparisons (Aave vs Compound) prefer get_lending_rates. Use when: Use for broad cross-protocol yield discovery. Call at most once per request — filter with min_apy, max_apy, min_tvl_usd, and symbols_any in a single call, then sort client-side rather than re-calling. For protocol-specific rate questions use get_lending_rates. Limitations: Third-party DeFiLlama analytics; up to 50 pools per call. The `symbol` field lists underlying tokens (e.g. 'ETH-USDC') — filter client-side instead of re-calling with different arguments. Reward APY indicates reward-dependent yield; do not present spot APY as durable. Alternatives: get_lending_rates, get_protocol_tvl, get_token_price

  ConnectorNo auth

• recommend_iconsA

  SupericonsA

  Recommend a coherent icon set for up to 20 named UI slots in one call. Uses task context to narrow ambiguous meanings. When context is insufficient, returns needs_clarification with labeled interpretation options instead of guessing. Invalid inputs and service failures return a plain-language reason and a next step instead of a bare protocol error. Returns one recommendation and optional alternatives for each resolved slot, with explicit public library labels and visual preview URLs where available. Library key si means Supericons, not Simple Icons.

  ConnectorNo auth

• read_docsA

  clipkitA

  Return a canonical Clipkit doc as text. topic "card" = the ~8KB compact authoring card — the recommended context for authoring; "pattern-lighting" = the shine/neon/glow technique rigs; "pattern-data-viz" / "pattern-cinematic-ui" / "pattern-ui-screencast" / "pattern-promo-teaser" = ~4-5KB pattern cards (proven idioms: count-ups and bar rows; product hero shots with camera rigs; faked app UI with typing/cursor/clicks) — load ONE alongside the card when the brief matches its archetype; "agents" = the full authoring guide (fetch only when the card doesn't cover a need); "protocol" = the formal field spec; "brand" = brand reference. (Same docs offered as MCP resources, exposed as a tool so you can read them directly — resources are not always model-readable.)

  ConnectorNo auth

• create_port_monitorA

  UptyBotsA

  Watch one TCP or UDP port on a host and report it up only when the service behind it actually answers. This is the type for game servers, databases, mail and anything else that speaks its own protocol rather than HTTP - Minecraft, Rust, CS2, FiveM, Postgres, Redis, SMTP. The port must be given as part of the url. Set protocol to UDP for game servers; most of them do not answer on TCP at all.

  ConnectorNo auth

• get_defi_tvlA

  flarewatchA

  Return total value locked (USD) across the Flare DeFi ecosystem with a per-protocol breakdown (protocol name, TVL, token count). Source is on-chain reads valued at current prices. available=false / total null when the price-dependent TVL read is unavailable.

  ConnectorNo auth