AppleSAFE
MCP servers for Apple apps (Notes, etc.) on macOS via AppleScript
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A collection of Model Context Protocol (MCP) servers that provide AI assistants with access to native Apple applications on macOS.
Servers
Requirements
- macOS 13+
- Node.js 18+ (22+ for Apple Messages)
- Full Disk Access granted to your terminal app (System Settings > Privacy & Security > Full Dis
e5339668df54OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add apple-reminders-mcp -- npx -y @griches/[email protected]
{
"mcpServers": {
"apple-reminders-mcp": {
"command": "npx",
"args": [
"-y",
"@griches/[email protected]"
]
}
}
}Exposed tools (60)
33 read · 17 write · 10 destructive. Blast radius: 10 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_contact_to_group | write | |
append_to_note | read | |
complete_reminder | read | |
create_contact | write | |
create_event | write | |
create_folder | write | |
create_group | write | |
create_list | write | |
create_note | write | |
create_reminder | write | |
delete_contact | destructive | |
delete_event | destructive | |
delete_folder | destructive | |
delete_group | destructive | |
delete_list | destructive | |
delete_message | destructive | |
delete_note | destructive | |
delete_reminder | destructive | |
drop_pin | destructive | |
flag_message | read | |
get_chat_messages | read | |
get_chat_participants | read | |
get_contact | read | |
get_directions | read | |
get_event | read | |
get_message | read | |
get_note | read | |
get_reminder | read | |
get_unread_count | read | |
list_all_events | read | |
list_calendars | read | |
list_chats | read | |
list_contacts | read | |
list_events | read | |
list_folders | read | |
list_groups | read | |
list_lists | read | |
list_mailboxes | read | |
list_messages | read | |
list_notes | read | |
list_reminders | read | |
mark_read | read | |
move_message | write | |
move_note | write | |
open_address | read | |
remove_contact_from_group | destructive | |
save_to_favorites | write | |
search_contacts | read | |
search_events | read | |
search_location | read | |
search_messages | read | |
search_notes | read | |
search_reminders | read | |
send_email | write | |
send_message | write | |
uncomplete_reminder | read | |
update_contact | write | |
update_event | write | |
update_note | write | |
update_reminder | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (7)
delete_contact, delete_event, delete_folder, delete_group, delete_list, delete_message, delete_note, delete_reminder, drop_pin, remove_contact_from_group
@modelcontextprotocol/sdk, zod, @types/node, typescript
@modelcontextprotocol/sdk, zod, @types/node, typescript
@modelcontextprotocol/sdk, zod, @types/node, typescript
@modelcontextprotocol/sdk, zod, @types/node, typescript
@modelcontextprotocol/sdk, zod, @types/node, typescript
Gates applied: no_behavioural_pass, no_license.
e5339668df54full audit observations/trust-audit/mcp-server/griches__apple-3.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | e5339668df54 | SAFE | B | 89 | first audit |
Questions
What is the Apple MCP server?
MCP servers for Apple apps (Notes, etc.) on macOS via AppleScript
What tools does Apple expose?
60 in total: 33 read-only, 17 that write, and 10 that can delete or overwrite (delete_contact, delete_event, delete_folder, delete_group, delete_list). Every one is listed on this page with its risk.
Is Apple safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 10 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Apple need?
No credential environment variables were found in its source, so it appears to need none.
How does Apple run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @griches/apple-reminders-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (e5339668df54), read on 2026-10-07. The repository is watched and re-audited when it changes.