{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github_mcp-supermemoryai-apple-mcp","slug":"mcp-supermemoryai-apple-mcp","name":"apple-mcp","type":"mcp","url":"https://github.com/supermemoryai/apple-mcp","page_url":"https://unfragile.ai/mcp-supermemoryai-apple-mcp","categories":["mcp-servers"],"tags":["applescripts","modelcontextprotocol"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github_mcp-supermemoryai-apple-mcp__cap_0","uri":"capability://tool.use.integration.mcp.compliant.tool.exposure.for.apple.applications","name":"mcp-compliant tool exposure for apple applications","description":"Implements a Model Context Protocol server that discovers and exposes Apple application functionality as standardized MCP tools through a dual-mode initialization strategy. The server uses eager and lazy module loading to manage eight distinct Apple application integrations (Notes, Mail, Messages, Calendar, Contacts, Reminders, Maps, Web Search), allowing MCP-compatible clients like Claude Desktop and Cursor IDE to discover and invoke these tools through a unified interface without direct AppleScript knowledge.","intents":["I want to expose my macOS automation capabilities to Claude Desktop or Cursor IDE without writing custom integrations","I need AI assistants to discover and call Apple application functions through a standard protocol","I want to enable natural language commands to control multiple Apple apps through a single MCP server"],"best_for":["macOS developers building AI-native workflows","teams integrating Claude Desktop with Apple ecosystem automation","developers migrating from direct AppleScript to MCP-based automation"],"limitations":["macOS-only — requires macOS 10.15+ with AppleScript and JXA support","Requires Bun runtime (not Node.js) for execution, limiting deployment to systems with Bun installed","Tool discovery is static at server startup — dynamic tool registration not supported","No built-in persistence layer for tool state across invocations"],"requires":["macOS 10.15 or later","Bun runtime (installed via brew install oven-sh/bun/bun)","MCP-compatible client (Claude Desktop, Cursor IDE, or custom MCP client)","TypeScript 4.5+ for development"],"input_types":["MCP tool call requests (JSON-RPC format)","natural language commands from MCP clients","structured tool parameters (strings, numbers, booleans, arrays)"],"output_types":["MCP tool response objects (JSON)","structured data from Apple applications","error responses with diagnostic information"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_1","uri":"capability://automation.workflow.applescript.and.jxa.based.application.automation.execution","name":"applescript and jxa-based application automation execution","description":"Executes automation commands against macOS applications by translating MCP tool calls into AppleScript (via run-applescript) or JavaScript for Automation (JXA via @jxa/run library). The system uses a hybrid approach where some applications (Messages, Mail) use AppleScript for reliability, while others (Notes, Contacts, Reminders, Calendar, Maps) use JXA for better performance and modern JavaScript syntax support. Each tool invocation is wrapped with error handling and safe mode checks to prevent unintended application state changes.","intents":["I want to send messages or read conversations from Messages app without manual interaction","I need to create, search, and read notes from Apple Notes programmatically","I want to search contacts, create calendar events, and manage reminders through code","I need to automate email operations (send, search, schedule delivery) without opening Mail manually"],"best_for":["automation engineers building macOS workflows","AI application developers needing native Apple app control","teams automating repetitive Apple app tasks (email, calendar, notes)"],"limitations":["AppleScript execution requires user approval via system dialogs on first run per application","JXA performance varies by application — some operations (large note searches) may timeout after 30 seconds","No transaction support — partial failures in multi-step operations leave applications in inconsistent state","Limited to applications with AppleScript/JXA support; third-party apps may not be automatable"],"requires":["macOS 10.15+ with AppleScript enabled","run-applescript npm package for AppleScript execution","@jxa/run npm package for JXA execution","User approval for application automation (System Preferences > Security & Privacy > Automation)"],"input_types":["tool parameters (message text, note content, email addresses, calendar details)","search queries (strings for notes, contacts, messages)","structured data (event objects, reminder definitions, contact information)"],"output_types":["application state data (message conversations, note content, contact records)","operation results (success/failure, created IDs, modified timestamps)","error messages with AppleScript/JXA stack traces"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_10","uri":"capability://safety.moderation.safe.mode.error.handling.and.operation.validation","name":"safe mode error handling and operation validation","description":"Implements a safety layer that validates automation operations before execution and provides detailed error context from AppleScript/JXA failures. Includes checks for invalid parameters (malformed email addresses, invalid dates), application state validation (checking if app is running), and graceful error recovery with diagnostic information. Errors include stack traces from automation runtime and suggestions for resolution, enabling developers to debug automation failures without direct AppleScript knowledge.","intents":["I want to understand why an automation operation failed with detailed error context","I need to validate parameters before attempting an operation to avoid partial failures","I want to handle errors gracefully and provide users with actionable error messages","I need to debug automation failures without reading AppleScript error codes"],"best_for":["developers building production automation workflows","teams requiring reliable error handling and diagnostics","builders of user-facing AI applications with automation"],"limitations":["Error recovery is passive — no automatic retry logic or fallback strategies","Validation is basic — complex business logic errors not caught pre-execution","Error messages are AppleScript/JXA stack traces — may be cryptic for non-developers","No support for transaction rollback — partial failures leave applications in inconsistent state"],"requires":["Error handling implemented in tool definitions","AppleScript/JXA error output captured and parsed"],"input_types":["operation parameters (any type)","application state information"],"output_types":["validation errors (parameter validation failures)","execution errors (AppleScript/JXA runtime errors with stack traces)","diagnostic suggestions (hints for resolution)"],"categories":["safety-moderation","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_11","uri":"capability://planning.reasoning.daisy.chaining.multi.step.automation.workflows","name":"daisy-chaining multi-step automation workflows","description":"Supports composition of multiple automation operations into single natural language requests through sequential tool invocation and data threading. Enables workflows like 'read notes, find contacts, send messages' where output from one operation feeds into the next without intermediate user interaction. The MCP server handles tool sequencing, data transformation between tools, and error propagation across the workflow. Allows AI clients to express complex multi-application workflows as single requests.","intents":["I want to read a note, extract contact information, and send a message based on the content","I need to search calendar for a meeting, find attendees in contacts, and send them an email","I want to create a reminder based on information from a note and calendar event","I need to search for a location, get directions, and send the route to a contact"],"best_for":["AI agents executing complex multi-application workflows","teams automating cross-application business processes","developers building sophisticated automation scenarios"],"limitations":["Workflow composition is client-side — server doesn't provide workflow orchestration primitives","No built-in transaction support — partial workflow failures leave applications in inconsistent state","Data transformation between tools is implicit — no schema validation between tool outputs and inputs","Error handling is sequential — failure in one step stops entire workflow"],"requires":["MCP client capable of multi-turn tool invocation (Claude Desktop, Cursor IDE)","AI model capable of planning multi-step workflows","All required applications installed and configured"],"input_types":["natural language request describing multi-step workflow","intermediate data from previous tool invocations"],"output_types":["final workflow result (output from last tool in sequence)","intermediate results (outputs from each step)","error messages (indicating which step failed)"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_2","uri":"capability://automation.workflow.natural.language.to.apple.notes.crud.operations","name":"natural language to apple notes crud operations","description":"Translates natural language requests into structured operations against Apple Notes through JXA automation. Supports listing all notes with metadata, searching notes by content or title, reading full note content with formatting, and creating new notes with specified content. The implementation uses @jxa/run to execute JavaScript directly in the Notes application context, providing access to note objects, folders, and metadata without requiring AppleScript syntax translation.","intents":["I want to search my notes for a specific topic and retrieve the full content","I need to create a new note with specific content from an AI response","I want to list all my notes with their creation dates and folder locations","I need to read a note by name and extract its content for processing"],"best_for":["knowledge workers using Notes as primary note-taking system","AI agents that need to augment responses with user's existing notes","developers building note-based knowledge management workflows"],"limitations":["Search is full-text only — no advanced query syntax (AND, OR, NOT operators)","Note formatting (bold, italics, links) is preserved but not exposed as structured metadata","Large note collections (>10,000 notes) may experience slow list operations","No support for note attachments or embedded media — only text content accessible"],"requires":["Apple Notes application installed and accessible","@jxa/run npm package","User approval for Notes automation in System Preferences"],"input_types":["search query strings (free-text search)","note content (plain text for creation)","note names/identifiers (for read operations)"],"output_types":["note objects with metadata (id, name, creation date, folder)","note content (plain text)","search result arrays with matching notes"],"categories":["automation-workflow","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_3","uri":"capability://automation.workflow.email.send.receive.and.search.with.scheduled.delivery","name":"email send, receive, and search with scheduled delivery","description":"Provides hybrid AppleScript/JXA-based email automation for Mail application, supporting message composition and sending, inbox/folder searching with query syntax, scheduled delivery (send at specific time), and message metadata retrieval. Uses AppleScript for reliability on send operations and JXA for search performance, with support for attachments, CC/BCC recipients, and HTML content. Integrates with Mail's native search indexing for fast query execution across large mailboxes.","intents":["I want to send an email with specific recipients, subject, and body content from an AI response","I need to search my email history for messages matching certain criteria and retrieve their content","I want to schedule an email to be sent at a specific time in the future","I need to retrieve metadata about recent emails (sender, subject, date) for summarization"],"best_for":["email-heavy workflows requiring AI-assisted composition and management","teams automating email notifications and scheduled communications","developers building email-integrated AI agents"],"limitations":["Scheduled delivery requires Mail to remain running — messages won't send if Mail is closed","Search is limited to Mail's built-in query syntax — complex boolean queries may fail","Attachment handling is basic — no support for attachment content inspection or transformation","HTML content rendering varies by Mail version — complex formatting may not preserve correctly"],"requires":["Apple Mail application installed and configured with email accounts","AppleScript and JXA execution permissions for Mail","User approval for Mail automation in System Preferences"],"input_types":["email composition parameters (to, cc, bcc, subject, body, html flag)","search queries (Mail query syntax: from:, subject:, date:, etc.)","scheduled delivery time (ISO 8601 timestamp)","attachment file paths"],"output_types":["send confirmation (success/failure with message ID)","search results (array of email objects with sender, subject, date, preview)","email metadata (full headers, body content, attachment list)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_4","uri":"capability://automation.workflow.message.sending.and.conversation.reading.from.messages.app","name":"message sending and conversation reading from messages app","description":"Enables sending iMessage and SMS messages through Messages application via AppleScript automation, and reading conversation history from specific contacts or group chats. Supports both text messages and rich content (emojis, formatting), with access to message timestamps, sender information, and conversation metadata. Uses AppleScript for reliability and direct application control, with error handling for invalid phone numbers/email addresses and network failures.","intents":["I want to send a message to a contact with specific content from an AI response","I need to read recent messages from a specific contact to provide context to an AI model","I want to send SMS or iMessage based on contact availability","I need to retrieve conversation history for analysis or summarization"],"best_for":["personal assistants and AI agents with messaging capabilities","teams automating customer communication workflows","developers building conversational AI with message context"],"limitations":["Requires Messages app to be running — messages queued while app is closed may not send","No support for group message creation — can only send to existing groups","Message read access is limited to visible conversation history — archived messages not accessible","Rich media (images, videos) not supported — text and emoji only"],"requires":["Apple Messages application installed and configured","AppleScript execution permissions for Messages","User approval for Messages automation in System Preferences","Valid phone numbers or email addresses for recipients"],"input_types":["recipient identifier (phone number or email address)","message content (text with emoji support)","conversation identifier (contact name or number for history retrieval)"],"output_types":["send confirmation (success/failure with timestamp)","conversation history (array of messages with sender, timestamp, content)","error messages (invalid recipient, network failure, etc.)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_5","uri":"capability://automation.workflow.calendar.event.search.and.creation.with.natural.language.dates","name":"calendar event search and creation with natural language dates","description":"Implements JXA-based calendar automation supporting event search by date range or keyword, creation of new calendar events with attendees and reminders, and retrieval of event details (time, location, attendees, notes). Supports natural language date parsing (e.g., 'next Tuesday', 'in 2 weeks') through client-side interpretation, with automatic timezone handling and conflict detection. Events are created in the default calendar or specified calendar with full iCal property support.","intents":["I want to search my calendar for events on a specific date or within a date range","I need to create a new calendar event with specific attendees, time, and location","I want to check for scheduling conflicts before proposing a meeting time","I need to retrieve event details (attendees, location, notes) for meeting preparation"],"best_for":["scheduling assistants and meeting coordination AI agents","teams automating calendar management and conflict detection","developers building calendar-aware AI applications"],"limitations":["Natural language date parsing is client-side only — server expects ISO 8601 timestamps","Attendee availability checking not supported — no integration with free/busy information","Recurring event creation is basic — no support for complex recurrence rules (e.g., 'every 2nd Tuesday')","No support for calendar sharing or delegation — events created in user's personal calendar only"],"requires":["Apple Calendar application installed and configured","@jxa/run npm package","User approval for Calendar automation in System Preferences","Calendar accounts configured in Calendar application"],"input_types":["date range (ISO 8601 start and end timestamps)","search keywords (event title, location, attendee name)","event creation parameters (title, start time, end time, location, attendees, notes, reminder)","calendar name (optional, defaults to primary calendar)"],"output_types":["event objects (id, title, start time, end time, location, attendees, notes)","search results (array of matching events)","creation confirmation (event ID, calendar URL)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_6","uri":"capability://automation.workflow.contact.search.and.phone.number.retrieval","name":"contact search and phone number retrieval","description":"Provides JXA-based contact management supporting full-text search across contact names, email addresses, and phone numbers, with retrieval of contact details (name, phone, email, organization, address). Search results include all contact information fields, enabling AI agents to disambiguate between similarly-named contacts and retrieve complete contact records for communication workflows. Supports fuzzy matching for name searches and returns contact metadata for further processing.","intents":["I want to search for a contact by name and retrieve their phone number or email","I need to find all contacts in a specific organization or with a particular email domain","I want to retrieve complete contact information (address, phone, email) for a person","I need to disambiguate between multiple contacts with similar names"],"best_for":["communication workflows requiring contact lookup and verification","AI agents automating message/email sending with contact resolution","teams building contact-aware scheduling and communication systems"],"limitations":["Search is full-text only — no advanced query syntax or field-specific search operators","Fuzzy matching is basic — typos in names may not match correctly","Contact groups are not returned — only individual contacts","No support for contact photo or custom fields — only standard vCard properties"],"requires":["Apple Contacts application installed and populated with contacts","@jxa/run npm package","User approval for Contacts automation in System Preferences"],"input_types":["search query (contact name, email, phone number, or organization)","search field (optional, defaults to all fields)"],"output_types":["contact objects (name, phone numbers, email addresses, organization, address)","search results (array of matching contacts with all fields)","error messages (no matches found, etc.)"],"categories":["automation-workflow","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_7","uri":"capability://automation.workflow.reminder.creation.and.search.with.due.date.management","name":"reminder creation and search with due date management","description":"Enables JXA-based reminder management supporting creation of new reminders with due dates, priority levels, and notes, as well as searching and listing reminders by status (completed/pending) or due date range. Supports both calendar-based reminders (with specific times) and all-day reminders, with automatic timezone handling. Reminders are created in the default Reminders list or specified list, with full support for reminder metadata (completion status, priority, notes).","intents":["I want to create a reminder for a specific task with a due date and priority","I need to search my reminders for incomplete tasks due within a date range","I want to list all pending reminders sorted by due date","I need to create a reminder with specific notes for context"],"best_for":["task management and productivity AI agents","teams automating reminder-based workflows and notifications","developers building task-aware AI assistants"],"limitations":["Reminder lists (categories) are limited to Reminders app's built-in lists — no custom list creation","Recurring reminders are basic — no support for complex recurrence patterns","No support for location-based reminders — only time-based reminders","Completion status is binary — no support for progress tracking or subtasks"],"requires":["Apple Reminders application installed","@jxa/run npm package","User approval for Reminders automation in System Preferences"],"input_types":["reminder title (task description)","due date (ISO 8601 timestamp or date string)","priority level (1-5 or 'high'/'medium'/'low')","notes (additional context)","list name (optional, defaults to default list)"],"output_types":["reminder objects (id, title, due date, priority, notes, completion status)","search results (array of matching reminders)","creation confirmation (reminder ID)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_8","uri":"capability://automation.workflow.maps.location.search.and.directions.retrieval","name":"maps location search and directions retrieval","description":"Implements JXA-based Maps integration supporting location search by address or landmark name, retrieval of location coordinates and metadata (address, phone, website), and directions generation between two locations with route details (distance, estimated time, turn-by-turn steps). Supports multiple route types (driving, walking, transit) with automatic selection based on context. Results include map URLs for opening locations in Maps application.","intents":["I want to search for a location by name or address and get its coordinates","I need to get directions from one location to another with estimated travel time","I want to retrieve business information (phone, website) for a location","I need to find nearby locations matching a search query"],"best_for":["location-aware AI assistants and navigation workflows","teams automating travel planning and logistics","developers building location-based AI applications"],"limitations":["Search results are limited to Maps' local search index — no web search integration","Directions are basic — no support for waypoints or multi-stop routing","Transit directions require macOS 11+ and may be unavailable in some regions","No support for real-time traffic or ETA updates — directions are static"],"requires":["Apple Maps application installed","@jxa/run npm package","User approval for Maps automation in System Preferences","Internet connection for location search and directions"],"input_types":["location query (address, landmark name, or business name)","start location (address or coordinates)","end location (address or coordinates)","route type (driving, walking, transit)"],"output_types":["location objects (name, address, coordinates, phone, website)","search results (array of matching locations)","directions (route summary with distance, time, turn-by-turn steps)","map URLs for opening in Maps application"],"categories":["automation-workflow","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-supermemoryai-apple-mcp__cap_9","uri":"capability://search.retrieval.duckduckgo.web.search.with.content.retrieval","name":"duckduckgo web search with content retrieval","description":"Provides HTTP-based web search integration using DuckDuckGo API, supporting keyword search with result ranking and content snippet retrieval. Returns search results with title, URL, and preview text without requiring API keys or authentication. Enables AI agents to augment responses with current web information and fact-checking capabilities. Results are ranked by relevance and include domain information for source credibility assessment.","intents":["I want to search the web for current information on a topic","I need to fact-check a claim by searching for supporting evidence","I want to retrieve recent news or updates on a specific subject","I need to find URLs and sources for a topic to provide citations"],"best_for":["AI agents requiring real-time web information augmentation","fact-checking and verification workflows","developers building research-aware AI assistants"],"limitations":["DuckDuckGo API has rate limiting — high-volume searches may be throttled","Search results are limited to text snippets — no full page content retrieval","No support for advanced search operators (site:, filetype:, etc.)","Results may include sponsored content or ads mixed with organic results"],"requires":["Internet connection","No API key required (uses DuckDuckGo public API)","HTTP client library (built-in to Node.js)"],"input_types":["search query (keyword string)","optional: result limit (number of results to return)"],"output_types":["search results array (title, URL, snippet, domain)","error messages (network failure, rate limit exceeded)"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":42,"verified":false,"data_access_risk":"high","permissions":["macOS 10.15 or later","Bun runtime (installed via brew install oven-sh/bun/bun)","MCP-compatible client (Claude Desktop, Cursor IDE, or custom MCP client)","TypeScript 4.5+ for development","macOS 10.15+ with AppleScript enabled","run-applescript npm package for AppleScript execution","@jxa/run npm package for JXA execution","User approval for application automation (System Preferences > Security & Privacy > Automation)","Error handling implemented in tool definitions","AppleScript/JXA error output captured and parsed"],"failure_modes":["macOS-only — requires macOS 10.15+ with AppleScript and JXA support","Requires Bun runtime (not Node.js) for execution, limiting deployment to systems with Bun installed","Tool discovery is static at server startup — dynamic tool registration not supported","No built-in persistence layer for tool state across invocations","AppleScript execution requires user approval via system dialogs on first run per application","JXA performance varies by application — some operations (large note searches) may timeout after 30 seconds","No transaction support — partial failures in multi-step operations leave applications in inconsistent state","Limited to applications with AppleScript/JXA support; third-party apps may not be automatable","Error recovery is passive — no automatic retry logic or fallback strategies","Validation is basic — complex business logic errors not caught pre-execution","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.5352134858278739,"quality":0.34,"ecosystem":0.46,"match_graph":0.25,"freshness":0.6,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.065Z","last_scraped_at":"2026-05-03T14:23:38.364Z","last_commit":"2025-08-11T03:13:27Z"},"community":{"stars":3076,"forks":273,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=mcp-supermemoryai-apple-mcp","compare_url":"https://unfragile.ai/compare?artifact=mcp-supermemoryai-apple-mcp"}},"signature":"1SiWsB5kEFRGSOtZjqLOTumyI15mL7IUUSgK5EKrdvwcAbxDnsDwknzFreufZoWRj/JDaoU/DpEouFlOP0fnAQ==","signedAt":"2026-06-20T03:04:00.557Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/mcp-supermemoryai-apple-mcp","artifact":"https://unfragile.ai/mcp-supermemoryai-apple-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=mcp-supermemoryai-apple-mcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}