"A server for finding home automation information" matching MCP tools:

• get_tier1_recommendationsA

  Tier1 IT AssessmentA

  Maps only stable Tier1 finding identifiers to approved Tier1 services and public resources. Call after a Tier1 score or email-domain check. Do not submit prose, URLs, customer information, or invented identifiers. This tool performs no arbitrary fetching, makes no contact request, changes nothing, and stores nothing.

  ConnectorNo auth

• get_corpus_coverageA

  SRI — MCP Server InspectorA

  No arguments. Returns how many MCP servers have been read at source level, and the share of them with each category of finding (credential access, network egress, install-time execution, prompt-injection surface). Use this to judge whether checking a specific server is worth it before you look one up. It reports aggregate counts only - no per-server findings, and no verdict about any individual server.

  ConnectorNo auth

• ui_builder_move_design_homeA

  Compose Preview CatalogsB

  Move a design's canonical home between this server and a repository checkout. This changes real authoritative state: quote the exact `baseRevision` and current `sourceHome` from ui_builder_get_design, provide a stable `operationId`, and name the new `targetHome`. The old server record remains as a retained copy pointing at the new home. The reply is an idempotent operation outcome with the new revision; a stale revision or changed source home is refused rather than overwriting a concurrent move. Unless the person already chose this move, call first with `dryRun: true`: it changes nothing and returns the choices to put to them — or, when your client supports form elicitation on this connection, asks them in a form and, if they choose to move, returns this move's outcome.

  ConnectorNo auth

• validate_bet_typeA

  MagicMarketsA

  Validate a bet_type string against a sport and get its human-readable description plus win/loss grid. An error means the string did not parse. Prefer copying bet_type values verbatim from list_event_offers rather than constructing them. Grammar: the first token is the direction ('for' to back, 'against' to lay), then the market and its arguments. Examples: 'for,h' home win, 'for,over,2.5' over 2.5 goals, 'for,ah,h,-4' Asian handicap home -1.0 (Asian lines are integers equal to 4x the real line), 'for,cs,2,1' correct score 2-1. Handicaps always refer to the home team.

  ConnectorOAuth

• validate_bet_typeA

  MagicMarketsA

  Validate a bet_type string against a sport and get its human-readable description plus win/loss grid. An error means the string did not parse. Prefer copying bet_type values verbatim from list_event_offers rather than constructing them. Grammar: the first token is the direction ('for' to back, 'against' to lay), then the market and its arguments. Examples: 'for,h' home win, 'for,over,2.5' over 2.5 goals, 'for,ah,h,-4' Asian handicap home -1.0 (Asian lines are integers equal to 4x the real line), 'for,cs,2,1' correct score 2-1. Handicaps always refer to the home team.

  ConnectorOAuth

• automation_deleteA

  Perspective AIA

  Permanently deletes an automation. Pauses any scheduled sends first, then removes the automation. Behavior: - DESTRUCTIVE and irreversible — the automation cannot be recovered. No undo. - Errors when the perspective or automation is not found, or you do not have access. Deleting an already-deleted automation errors as well. - If pausing the scheduled sender fails, the deletion is aborted and you'll get success: false with "Failed to stop running workflow. Please try again." — the automation stays intact in that case. When to use this tool: - The user explicitly asked to remove an automation and confirmed. - Cleaning up a misconfigured automation that automation_test repeatedly fails on. When NOT to use this tool: - The user just wants to pause it temporarily — use automation_update with { enabled: false } instead. - You're not sure which automation_id is correct — confirm via automation_list first.

  Connector

  Destructive

  OAuth

• dcl_evaluate_walletA

  DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)A

  POST-ACTION Wallet Secret Guardian ($0.02). Scans for BIP-39 seed phrases (12 or 24 consecutive wordlist words), raw hex or WIF-format private keys, Ethereum/Bitcoin wallet addresses, and API keys/bearer tokens appearing near wallet/custody/signing terminology. Any finding results in NO_COMMIT — wallet secrets have no safe threshold, unlike other DCL evaluators. Returns a `sanitized_output` with all matches redacted (null if nothing was found) and a masked `redacted_sample` per finding — the real value is never returned or stored server-side.

  ConnectorNo auth

• ios_drag_dropA

  Robot Actions — Remote Device ControlB

  Drag-and-drop on an iOS device: hold at (x1,y1) for holdMs to grab, then move to (x2,y2) over durationMs. Distinct from ios_swipe (no explicit hold). Use for home-screen icon reorder, drag-into-folder, slide-to-confirm. Coordinates are screen points. Works without an automation session when the direct input path is available; falls back to one otherwise (see `input`).

  ConnectorOAuth

• ios_rebootA

  Robot Actions — Remote Device ControlB

  Reboot an iOS device. DISRUPTIVE and NOT REVERSIBLE: the device is unreachable for roughly a minute, the automation session and the stream go down, and anything in progress on the device is lost. Requires confirm=true — there is no default. Do NOT reach for this to recover from a flaky tool call; try ios_end_session first, which resets the automation session without touching the device. Reboot only when the device itself is wedged and a human has asked for it. No automation session required. The Android counterpart is device_reboot.

  Connector

  Destructive

  OAuth

• withdraw_findingA

  northreachB

  Retract support for a finding you authored, with a reason. Original content remains visible and labeled withdrawn. Identical retries are safe; this does not claim the finding is disproven.

  ConnectorNo auth

• list_skillsA

  mcpA

  START HERE for any open-ended request. Lists the task playbooks this server supports — systematic learning from bookmarks, organising into themes, cleaning up, X-list intelligence, exporting data out, finding a half-remembered save, digests, and diagnosing sync. Each names when to use it; call get_skill for the exact tool sequence.

  ConnectorNo auth

• goal-register-iteration-findingA

  Planner (proof-of-done)A

  Register an immutable LeanSolver finding against the currently tracked goal contract. subjectRefs must be goal-scoped refs of kind goal, criterion, or assumption. Returns the server-generated finding id to pass later as addressesFindingId; rejects stale contract tracking.

  ConnectorNo auth

• goal-register-iteration-findingA

  Planner MCP — provable "done" for AI agentsA

  Register an immutable LeanSolver finding against the currently tracked goal contract. subjectRefs must be goal-scoped refs of kind goal, criterion, or assumption. Returns the server-generated finding id to pass later as addressesFindingId; rejects stale contract tracking.

  ConnectorNo auth

• device_uhid_key_pressA

  Robot Actions — Remote Device ControlB

  Send a key press/release via UHID keyboard (id=2). Uses the device control protocol's boot keyboard interface. On first call, CREATE is sent automatically. modifiers bitmask: bit0=LCtrl, bit1=LShift, bit2=LAlt, bit3=LMeta, bit4=RCtrl, bit5=RShift, bit6=RAlt, bit7=RMeta. keycode is the HID usage ID (0x04=a, 0x28=Enter, 0x29=Escape). Send keycode=0 with modifiers=0 to release. device_key is the higher-level twin: it accepts named keys (HOME, ENTER, ...) instead of raw usage IDs and falls back automatically when a key needs policy-level handling. Prefer device_key for normal automation; reach for this one only when injected key events are filtered.

  ConnectorOAuth

• ios_unlockA

  Robot Actions — Remote Device ControlB

  Wake the device with the keyboard Home key: it lights a dark display and clears a passcode-free Lock Screen without closing whatever app was open, so it is safe to call at ANY time — even on an already-awake device, since it never navigates away from the foreground. Needs NO automation session, because the automation runner itself cannot launch while the Lock Screen is frontmost. If that wake could not be sent at all (older iOS, or no active input channel), an alternate wake-and-swipe is used instead; dismissLockScreen additionally forces that alternate swipe for a caller who can see the Lock Screen is still showing (DANGER: this swipe goes to the Home screen on an already-unlocked device). The reply reports only what it can observe (display dark or lit); it cannot confirm whether a Lock Screen is still showing. A passcode is never bypassed.

  ConnectorOAuth

• list-automations-toolA

  0bull Phone FarmA

  List the authenticated user's automations. An automation is a saved task for the AI phone agent (`prompt`) that runs across one or more phones, on a schedule (`schedule_cron` in `timezone`), when its webhook is called, or on demand with run-automation-tool. Each run is followed with list-automation-runs-tool and get-automation-run-tool. `kind` is "prompt" for that, or "tiktok_warmup" for a TikTok account warm-up: its `settings` (niche, keywords, comment language, daily window, session counts and lengths) replace `prompt` and it has no `schedule_cron` — it plans and runs its own sessions every day on its own timetable, and run-automation-tool only ever starts an extra one now. Not the same as macros (list-macros-tool), which replay recorded input exactly with no AI. Automations are created and edited in the web app.

  ConnectorOAuth

• list_housesA

  hausA

  List the households the current user belongs to (e.g. to tell the user which home you are acting on). The active house is determined server-side from the authenticated session.

  ConnectorNo auth

• get_bundle_purchase_marketA

  LastLook DataA

  Returns a home purchase market bundle: current 30yr mortgage rate, median US home sale price (MSPUS), estimated monthly P&I payment on the median home assuming 20% down, annual income required to qualify at 28% DTI, affordability level signal, and housing starts. Directly answers "can my client afford a home today?" Priced at $0.60 USDC via x402 on Base.

  ConnectorNo auth

• delete-automationA

  Apdf — PDF Tracking & AnalyticsA

  Delete an automation and its execution history. To keep the rule and only stop it from firing, use "deactivate-automation".

  Connector

  Destructive

  OAuth

• list_checksA

  TrustAI VerificationA

  Return the structural checks this server performs on legal-AI output, and — explicitly — what it never claims. Information, not legal advice.

  ConnectorNo auth

• list-brand-kitsA

  CanvaB

  Find or browse the Canva Brand Kits available to the user. A Brand Kit is an organisation's high-level home for brand styles and assets, such as colors, fonts, and logos. Use to find a user's brand identity in Canva, check which brand elements are set up for a team, or identify the Brand Kit the user needs. Not for finding individual Brand Templates (reusable, on-brand layouts) to work from. Returns each Brand Kit's brand_kit_id, name, and thumbnail.

  ConnectorOAuth