High-risk tools in Apple Shortcuts

Run a named Apple Shortcut, optionally with text input. Use this tool to execute any shortcut the user has in their Shortcuts library. Args: - name (string): The exact name ...

Navigate to a URL. Opens the browser if not already running. Only http: and https: URLs are accepted (plus the special about:blank). Other URL schemes (file:, chrome:, chrome-e...

Wait for an element to appear or for a specified time.

Animate a character with facial expressions and body movements from a reference performance video (Act-Two).

Run multiple GA4 reports (max 5) in a single batch request. Each report shares the row-volume safety net of ga_run_report.

Run a GA4 pivot report. Pivots are useful for cross-tabulating dimensions (e.g. country x device).

Run a GA4 realtime report with configurable dimensions and metrics. Realtime data covers the last 30 minutes by default.

Run a GA4 report with configurable dimensions, metrics, date range, ordering, and safe dataset controls. Estimates row count first; returns a warning above row_warning_threshold...

Stop an ongoing call immediately. WHEN TO USE: - User wants to end a call in progress - Call is stuck or behaving unexpectedly - Emergency stop COMMON MISTAKES: - Calling this...

Submit a task ID and wait for it to complete. Polls automatically.

Open a visible browser window so the user can log in manually. The session is saved automatically. WHEN TO USE:

Navigate back in browser history.

Navigate forward in browser history.

Hover over an element (triggers hover menus/tooltips).

Translate and dub audio into a different language, cloning the original speaker\

Forward an email to other recipients.

Isolate voice from background audio. Extracts clean speech. Input must be 4.6s-3600s.

Generate a short audio preview of a voice from a text description, without creating it.

Reply to an email message.

Execute a raw SOQL query. For advanced queries only — prefer dedicated tools for standard operations. Max 200 records enforced.

Replace the voice in an audio or video file with a different voice, preserving speech content.

Add recipients to a Mixmax sequence, enrolling them in the automated email drip campaign. IMPORTANT: Confirm with the user before calling — this adds real people to a live sequ...

Click an element. Use @ref from browser_snapshot (preferred) or a CSS selector. WORKFLOW: browser_snapshot → find @ref → browser_click @ref

Close the browser session. Sessions are saved automatically.

Clear a field and fill it with text. Use @ref from browser_snapshot. WORKFLOW: browser_snapshot → find input @ref → browser_fill

Press a keyboard key. Common keys: Enter, Tab, Escape, Backspace, ArrowDown, ArrowUp.

Scroll the page in a direction.

Select an option from a dropdown.

Type text character by character (simulates real keystrokes). Useful for search boxes and autocompletes that respond to individual key events.

Create a custom voice from a text description of desired voice characteristics.

Create an outbound phone call using a Retell AI voice agent. WHEN TO USE: User asks you to make, place, or initiate a phone call. WORKFLOW (typical sequence): 1. list_agents →...

Create a browser-based voice call session. Returns a web_call_link the user can open to talk to a Retell agent. WHEN TO USE: - User wants a voice call in their browser instead ...

Generate one or more images using OpenAI

Animate a still image into a video using AI.\n\n

Create an AI-generated video from a text description.\n\n

Generate music from a text prompt using ElevenLabs Music API.

Generate music from a composition plan (created by create_music_plan or manually crafted).

Generate sound effects from a text description.

Generate spoken audio from text using ElevenLabs text-to-speech.

Animate a still image into a video. Supports first-frame (and optionally last-frame) keyframe control.

Create a video entirely from a text description.

Re-style or transform an existing video using Gen-4 Aleph.

Generate images from text descriptions using Google Gemini

Generate a professional visual (diagram, infographic, illustration) from text using Napkin AI.

Create a censor job that processes a specific clip and bleeps / mutes profanity.

Export all clips from a collection. Returns a

Connect an Outreach account via OAuth. Takes no parameters — call with {}. Initiates OAuth flow — in standalone mode, opens a browser URL for sign-in. In bridge mode, delegates...

Publish a specific agent version, making it the active/live version. WHEN TO USE: - After updating an agent

Set up SSH keys and configuration for connecting to Replit projects. Generates an Ed25519 key pair, configures ~/.ssh/config, and provides the public key for the user to add to ...

Connect a Salesforce account via OAuth. Takes no parameters — call with {}. Initiates OAuth flow — in standalone mode, opens a browser URL for Salesforce sign-in. In bridge mod...