About Apple Reminders
Apple Reminders is an MCP server for managing reminders on macOS through EventKit, for workflows that let agents read and maintain tasks. It supports list and reminder operations, along with permission checks and planning prompts.
Key features
- 01Discover, create, and delete reminder lists
- 02List, create, update, and delete reminders
- 03Complete or reopen tasks
- 04Provide today and list resources
- 05Check health and access permissions
Use cases
- 01Organize to-dos and follow-ups with an agent
- 02Manage reminders separately from other Apple services
- 03Check reminder access and diagnose permission issues
MCP support
The MCP server exposes tools, resources, and prompts for reminder lists and tasks to clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
17Saved tool list · updated 1d ago
This tool takes no parameters.
Details
From the project READMEApple Reminders MCP
MCP server for Apple Reminders on macOS.
Provides access to reminder lists and tasks through EventKit. Keep Reminders as the system of record while enabling agents to read, create, update, complete, and delete reminders.
When to use
- Task and reminder workflows
- Reminders isolated from the rest of the Apple stack
- EventKit-backed reminder management
What It Does
- Discover, create, and delete reminder lists
- List, create, update, and delete reminders
- Complete and uncomplete tasks
- Tool discovery helpers
search_toolsandget_tool_infofor context-constrained clients - Today and list resources
- Planning and inbox-triage prompts
- Health and permission checks:
reminders_health,reminders_permission_guide,reminders_recheck_permissions
Install On This Mac
Quick start (uvx, from PyPI)
With uv installed:
uvx apple-mcp-reminders
No clone, no venv management.
From a clone
git clone https://github.com/JonathanRReed/Apple-MCPs.git
cd Apple-MCPs
uv sync --all-packages
This builds one workspace environment with every server's entry point in .venv/bin (for example .venv/bin/apple-reminders-mcp). You can also point an MCP client at AppleReminders-MCP/start.sh, which prefers uv run and falls back to a plain venv bootstrap (Python 3.11+ required).
Install In AI Agents
Generic MCP client config
{
"mcpServers": {
"apple-reminders": {
"command": "uvx",
"args": ["apple-mcp-reminders"],
"env": {
"APPLE_REMINDERS_MCP_SAFETY_MODE": "safe_manage"
}
}
}
}
Running from a clone instead? Use /path/to/Apple-MCPs/AppleReminders-MCP/start.sh as the command with empty args.
Claude Code example
claude mcp add --transport stdio --scope user apple-reminders -- uvx apple-mcp-reminders
--scope user makes the server available in every project. To share it with one repository through its .mcp.json instead, use --scope project.
Safety Modes
safe_readonlysafe_managefull_access
Transport
stdio is the default and recommended transport. Set APPLE_REMINDERS_MCP_TRANSPORT=streamable-http (with optional APPLE_REMINDERS_MCP_HOST and APPLE_REMINDERS_MCP_PORT) to serve Streamable HTTP instead.
macOS Permissions
- Reminders access is required
Launch Checklist
- Add
uvx apple-mcp-reminders(or a clone'sAppleReminders-MCP/start.sh) to your MCP client - Reload or reconnect the client so the Reminders tool surface is loaded into context
- Call
reminders_healthfirst - If Reminders access is blocked, call
reminders_permission_guide - After changing macOS permissions, call
reminders_recheck_permissions
Prompting Notes
tools/listreturns the full Reminders tool surface. Context-constrained clients can usesearch_toolsfirst, thenget_tool_infofor the Reminders tool they need.- Reminders are organized into lists. Identify available lists on first use and set a default.
- Use Reminders for due items, tasks, and follow-ups.
due_daterequires a timezone offset:yyyy-MM-ddTHH:mm:ss-HH:00
Related
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.