The Apple MCP server provides a unified interface to interact with native Apple apps and services:
Contacts: Search and retrieve contacts
Notes: Search, list, and create notes
Messages: Send, read, schedule, and check unread messages
Mail: Read unread emails, search emails, send emails with attachments, list mailboxes
Reminders: Search, create, list, and open reminders
Web Search: Search the web using DuckDuckGo and retrieve content
Calendar: Search, create, open, and list calendar events
Maps: Search locations, save favorites, get directions, manage guides, and add places to guides
Enables interaction with native Apple applications and services, providing access to Messages, Notes, Contacts, Mail, Reminders, and Calendar for sending messages, reading/searching notes, managing contacts, sending/scheduling emails, creating reminders, and managing calendar events.
Mentioned as a planned future feature to search and open music in Apple Music app.
Enables web search functionality using DuckDuckGo to retrieve and process content from search results.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Apple MCP send a message to John Doe about our meeting tomorrow at 3pm"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is a collection of apple-native tools for the MCP protocol.
Here's a step-by-step video about how to set this up, with a demo. - https://x.com/DhravyaShah/status/1892694077679763671
{
"mcpServers": {
"apple-mcp": {
"command": "bunx",
"args": ["--no-cache", "apple-mcp@latest"]
}
}
To install Apple MCP for Claude Desktop automatically via Smithery:
npx -y @smithery/cli@latest install @Dhravya/apple-mcp --client claude... and for cursor, you can do:
npx -y @smithery/cli@latest install @Dhravya/apple-mcp --client cursorMessages:
Send messages using the Apple Messages app
Read out messages
Notes:
List notes
Search & read notes in Apple Notes app
Contacts:
Search contacts for sending messages
Emails:
Send emails with multiple recipients (to, cc, bcc) and file attachments
Search emails with custom queries, mailbox selection, and result limits
Schedule emails for future delivery
List and manage scheduled emails
Check unread email counts globally or per mailbox
Reminders:
List all reminders and reminder lists
Search for reminders by text
Create new reminders with optional due dates and notes
Open the Reminders app to view specific reminders
Calendar:
Search calendar events with customizable date ranges
List upcoming events
Create new calendar events with details like title, location, and notes
Open calendar events in the Calendar app
Web Search:
Search the web using DuckDuckGo
Retrieve and process content from search results
Maps:
Search for locations and addresses
Save locations to favorites
Get directions between locations
Drop pins on the map
Create and list guides
Add places to guides
TODO: Search and open photos in Apple Photos app
TODO: Search and open music in Apple Music app
You can also daisy-chain commands to create a workflow. Like: "can you please read the note about people i met in the conference, find their contacts and emails, and send them a message saying thank you for the time."
(it works!)
You just need bun, install with brew install oven-sh/bun/bun
Now, edit your claude_desktop_config.json with this:
{
"mcpServers": {
"apple-mcp": {
"command": "bunx",
"args": ["@dhravya/apple-mcp@latest"]
}
}
}Now, ask Claude to use the apple-mcp tool.
Can you send a message to John Doe?find all the notes related to AI and send it to my girlfriendcreate a reminder to "Buy groceries" for tomorrow at 5pmRelated MCP server: Local MCP
git clone https://github.com/dhravya/apple-mcp.git
cd apple-mcp
bun install
bun run index.tsenjoy!
Search, create, and open calendar events in Apple Calendar app
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform: 'search', 'open', 'list', or 'create' | |
| searchText | No | Text to search for in event titles, locations, and notes (required for search operation) | |
| eventId | No | ID of the event to open (required for open operation) | |
| limit | No | Number of events to retrieve (optional, default 10) | |
| fromDate | No | Start date for search range in ISO format (optional, default is today) | |
| toDate | No | End date for search range in ISO format (optional, default is 30 days from now for search, 7 days for list) | |
| title | No | Title of the event to create (required for create operation) | |
| startDate | No | Start date/time of the event in ISO format (required for create operation) | |
| endDate | No | End date/time of the event in ISO format (required for create operation) | |
| location | No | Location of the event (optional for create operation) | |
| notes | No | Additional notes for the event (optional for create operation) | |
| isAllDay | No | Whether the event is an all-day event (optional for create operation, default is false) | |
| calendarName | No | Name of the calendar to create the event in (optional for create operation, uses default calendar if not specified) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While it mentions the four operations, it doesn't describe what each operation actually does (e.g., 'open' might open the Calendar app, 'list' might retrieve events), nor does it mention permissions needed, whether operations are read-only or mutating, rate limits, or what happens on success/failure. For a multi-operation tool with no annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that states the core functionality without any wasted words. It's appropriately sized and front-loaded with the essential information. Every word earns its place in this concise formulation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (13 parameters, 4 distinct operations) and the absence of both annotations and output schema, the description is insufficient. It doesn't explain what each operation does, what the tool returns, or any behavioral characteristics. For a multi-operation tool with no structured metadata beyond the input schema, the description should provide more operational context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema already documents all 13 parameters thoroughly with descriptions, enums, and required/optional status. The description adds no additional parameter information beyond what's in the schema. According to guidelines, when schema coverage is high (>80%), the baseline is 3 even with no param info in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'Search, create, and open calendar events in Apple Calendar app' - a specific verb+resource combination. It distinguishes this from sibling tools like contacts, mail, maps, etc. by focusing on calendar events. However, it doesn't differentiate between the four operations (search, open, list, create) within the tool itself, which keeps it from a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives or when to use specific operations within the tool. There's no mention of prerequisites, constraints, or comparison with other calendar-related tools that might exist. The agent must infer usage entirely from the parameter descriptions in the schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search and retrieve contacts from Apple Contacts app
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Name to search for (optional - if not provided, returns all contacts). Can be partial name to search. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions 'Search and retrieve' but doesn't disclose behavioral traits such as permissions needed, rate limits, whether it's read-only or destructive, or what the return format looks like. This leaves significant gaps for a tool with no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('Search and retrieve contacts') without unnecessary words. It earns its place by clearly stating the tool's function in a compact form.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what 'retrieve' entails (e.g., what data is returned, format, or pagination), nor does it cover behavioral aspects like safety or constraints, making it inadequate for a search tool with no structured output documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add meaning beyond the input schema, which has 100% coverage and fully documents the single optional parameter 'name'. Since schema coverage is high, the baseline score of 3 is appropriate, as the description doesn't compensate with extra details like search syntax or examples.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Search and retrieve') and resource ('contacts from Apple Contacts app'), making the purpose evident. However, it doesn't differentiate this tool from potential sibling tools like 'calendar' or 'mail' in terms of domain specificity beyond mentioning 'Apple Contacts app'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'mail' or 'messages', nor does it mention any prerequisites or exclusions. It implies usage for contact-related searches but lacks explicit context or comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Interact with Apple Mail app - read unread emails, search emails, and send emails
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform: 'unread', 'search', 'send', 'mailboxes', 'accounts', or 'latest' | |
| account | No | Email account to use (optional - if not provided, searches across all accounts) | |
| mailbox | No | Mailbox to use (optional - if not provided, uses inbox or searches across all mailboxes) | |
| limit | No | Number of emails to retrieve (optional, for unread, search, and latest operations) | |
| searchTerm | No | Text to search for in emails (required for search operation) | |
| to | No | Recipient email address (required for send operation) | |
| subject | No | Email subject (required for send operation) | |
| body | No | Email body content (required for send operation) | |
| cc | No | CC email address (optional for send operation) | |
| bcc | No | BCC email address (optional for send operation) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions three operations but omits three others listed in the schema (mailboxes, accounts, latest). It doesn't describe authentication requirements, rate limits, side effects, or what happens when operations fail. For a multi-operation tool with 10 parameters, this is insufficient behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately concise with a single sentence that front-loads the core purpose. It efficiently communicates the tool's scope without unnecessary elaboration. Every word earns its place, though it could be slightly more structured by explicitly listing all operations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 10 parameters, 6 operations, and no annotations or output schema, the description is incomplete. It omits three operations entirely and provides no behavioral context about authentication, side effects, or error handling. The agent would struggle to use this tool effectively without trial and error.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing comprehensive parameter documentation. The description adds minimal value beyond the schema by listing three main operations, but doesn't explain parameter dependencies or operational semantics. The baseline of 3 is appropriate since the schema does the heavy lifting, though the description could have better explained how operations relate to parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as interacting with Apple Mail app with specific operations (read unread emails, search emails, send emails). It distinguishes from sibling tools like calendar or contacts by focusing on email functionality. However, it doesn't explicitly differentiate from potential email-related tools that might exist elsewhere.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, appropriate contexts for different operations, or when other tools might be more suitable. The agent must infer usage solely from the operation names and parameter descriptions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search locations, manage guides, save favorites, and get directions using Apple Maps
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform with Maps | |
| query | No | Search query for locations (required for search) | |
| limit | No | Maximum number of results to return (optional for search) | |
| name | No | Name of the location (required for save and pin) | |
| address | No | Address of the location (required for save, pin, addToGuide) | |
| fromAddress | No | Starting address for directions (required for directions) | |
| toAddress | No | Destination address for directions (required for directions) | |
| transportType | No | Type of transport to use (optional for directions) | |
| guideName | No | Name of the guide (required for createGuide and addToGuide) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions actions like 'save favorites' and 'get directions' which imply mutation and read operations, but doesn't clarify permissions, rate limits, data persistence, or response formats. For a multi-operation tool with no annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured as a single sentence listing key capabilities. It's appropriately sized for a multi-function tool, though it could be more front-loaded by emphasizing the primary 'operation' parameter requirement. Every phrase earns its place by describing distinct functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 9 parameters, 7 distinct operations, no annotations, and no output schema, the description is inadequate. It doesn't explain how operations differ, what data is returned, error conditions, or authentication requirements. The agent lacks sufficient context to use this tool effectively without trial and error.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing good documentation for all 9 parameters. The description adds minimal value beyond the schema, only implying that operations like 'search locations' correspond to the 'search' operation parameter. It doesn't explain parameter interactions or provide additional context beyond what's already in the structured schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs (search, manage, save, get) and resources (locations, guides, favorites, directions) using Apple Maps. It distinguishes itself from sibling tools like calendar or contacts by focusing on mapping functionality, though it doesn't explicitly differentiate from potential mapping alternatives within the same domain.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives or when not to use it. It lists capabilities but offers no context about appropriate use cases, prerequisites, or comparisons with other tools. The agent must infer usage solely from the operation list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Interact with Apple Messages app - send, read, schedule messages and check unread messages
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform: 'send', 'read', 'schedule', or 'unread' | |
| phoneNumber | No | Phone number to send message to (required for send, read, and schedule operations) | |
| message | No | Message to send (required for send and schedule operations) | |
| limit | No | Number of messages to read (optional, for read and unread operations) | |
| scheduledTime | No | ISO string of when to send the message (required for schedule operation) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions operations like 'send' and 'schedule', implying mutations, but doesn't state permissions needed, rate limits, or what 'check unread messages' entails (e.g., returns count or list). This leaves significant gaps in understanding the tool's behavior and constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, using a single sentence to list key operations. Every word contributes to understanding the tool's scope. However, it could be slightly more structured by separating operations or adding brief context, but it avoids waste and is efficiently phrased.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 parameters, multiple operations including mutations) and lack of annotations and output schema, the description is incomplete. It doesn't cover behavioral aspects like error handling, return values, or operational constraints. For a multi-operation tool with no structured support, more detail is needed to guide effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 5 parameters with descriptions and enums. The description adds minimal value beyond listing operations, as it doesn't explain parameter interactions or provide additional context. For example, it doesn't clarify that 'phoneNumber' is required for specific operations beyond what the schema states. Baseline 3 is appropriate given high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Interact with Apple Messages app - send, read, schedule messages and check unread messages.' It specifies the verb ('interact with') and resource ('Apple Messages app'), listing four distinct operations. However, it doesn't differentiate from sibling tools like 'contacts' or 'mail' beyond mentioning the specific app, which is good but not fully distinguishing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It lists operations but doesn't mention prerequisites, context, or exclusions. For example, it doesn't clarify if 'send' requires specific permissions or if 'read' is for recent messages only. With sibling tools like 'mail' and 'contacts', no differentiation is offered, leaving usage ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search, retrieve and create notes in Apple Notes app
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform: 'search', 'list', or 'create' | |
| searchText | No | Text to search for in notes (required for search operation) | |
| title | No | Title of the note to create (required for create operation) | |
| body | No | Content of the note to create (required for create operation) | |
| folderName | No | Name of the folder to create the note in (optional for create operation, defaults to 'Claude') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions operations but doesn't describe what happens during each (e.g., search returns matching notes, list returns all notes, create adds a new note). It lacks details on permissions, rate limits, error handling, or whether operations are read-only or mutative (create implies mutation). The description is too vague for a tool with multiple operations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose. It wastes no words but could be more structured by separating operations or adding brief context. Given the tool's multi-operation nature, a bit more detail might improve clarity without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 5 parameters, no annotations, no output schema, and multiple operations (search, list, create), the description is incomplete. It doesn't explain return values, error conditions, or behavioral nuances. The schema covers parameters, but the description fails to add necessary context for safe and effective use, especially given the mutative 'create' operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 5 parameters and their purposes. The description adds no parameter-specific information beyond what's in the schema (e.g., it doesn't explain search behavior, list scope, or create defaults). Baseline is 3 since the schema handles parameter semantics adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('search, retrieve and create') and resource ('notes in Apple Notes app'). It distinguishes this tool from siblings like calendar or contacts by specifying the Apple Notes domain. However, it doesn't explicitly differentiate 'retrieve' from 'list' operations or mention that 'retrieve' might refer to listing notes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., Apple Notes app availability), when to choose search vs. list operations, or how this tool relates to sibling tools like reminders or messages for note-taking tasks. Usage is implied through the operation parameter but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search, create, and open reminders in Apple Reminders app
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform: 'list', 'search', 'open', 'create', or 'listById' | |
| searchText | No | Text to search for in reminders (required for search and open operations) | |
| name | No | Name of the reminder to create (required for create operation) | |
| listName | No | Name of the list to create the reminder in (optional for create operation) | |
| listId | No | ID of the list to get reminders from (required for listById operation) | |
| props | No | Properties to include in the reminders (optional for listById operation) | |
| notes | No | Additional notes for the reminder (optional for create operation) | |
| dueDate | No | Due date for the reminder in ISO format (optional for create operation) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the operations (search, create, open) but fails to disclose critical traits like required permissions (e.g., app access), side effects (e.g., data persistence), rate limits, or error handling. For a multi-operation tool with potential mutations, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core functionality ('search, create, and open reminders') without any wasted words. It's appropriately sized for the tool's scope, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (8 parameters, multiple operations including mutations) and lack of annotations and output schema, the description is incomplete. It doesn't cover behavioral aspects, usage context, or return values, leaving significant gaps for an agent to operate effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with detailed parameter descriptions in the input schema. The description adds no additional meaning beyond the schema, such as explaining inter-parameter dependencies or usage examples. Given the high schema coverage, the baseline score of 3 is appropriate, as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('search, create, and open') and resource ('reminders in Apple Reminders app'), making it immediately understandable. However, it doesn't explicitly distinguish this tool from its siblings like 'calendar' or 'notes', which might also manage time-based or task-related data, missing full differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as its sibling tools (e.g., 'calendar' for events, 'notes' for general notes). It lacks explicit context, prerequisites, or exclusions, leaving the agent to infer usage based on the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
calendarcontactsmailmapsmessagesnotesremindersEach tool corresponds to a distinct Apple app (Calendar, Contacts, Mail, Maps, Messages, Notes, Reminders) with clearly separated purposes. There is no overlap in functionality, as each tool handles a specific domain like events, contacts, emails, locations, messages, notes, or reminders, making tool selection straightforward for an agent.
All tool names are singular nouns (calendar, contacts, mail, maps, messages, notes, reminders) that directly reference the Apple apps they interact with. This consistent naming pattern is simple, predictable, and enhances readability across the tool set.
With 7 tools, the server is well-scoped for its purpose of interacting with Apple's core productivity apps. Each tool earns its place by covering a major app, avoiding bloat while providing comprehensive coverage across common user workflows like communication, organization, and navigation.
The tool set offers strong coverage for basic CRUD operations across key Apple apps, such as searching, creating, and retrieving items. Minor gaps exist, like no explicit update or delete operations in some tools (e.g., notes, reminders), but agents can likely work around this using create and search functions for most use cases.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Let ChatGPT, Claude & Cursor use your Mac: email, calendar, iMessage, Teams, files. Local, free.
Search, read, and write your Apple Notes from ChatGPT/Claude via a local Mac agent + MCP relay.
MCP connector for iMessage & Contacts via a local Mac agent + Vercel relay
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jxnl/apple-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
