AgentPod is building a private, secure device for your AI agent.The AgentPod device is coming.Coming soonBe first
We checked this and rejected itprivacy

Apple MCP: why it is not safe to use

We found broad delete and send capabilities plus access to local Messages data, so this skill needs careful use and tighter safeguards.

What we found

Our review did not find hidden instructions, hardcoded secrets, obfuscated code, privilege escalation, or undisclosed data transfer to a third party. The main concern is scope and sensitivity of access on the local Mac.

This skill can delete notes, folders, reminders, contacts, and calendar items, and it can send mail or messages. The README describes optional safety flags, but in normal mode these actions are available without a built in confirmation step.

We also found that the Messages component reads the local Messages database at `~/Library/Messages/chat.db` and requires Full Disk Access. Mail and Messages features can expose private communications, which raises privacy risk, especially for non-technical users.

What to do instead

Use this skill only if you need these app integrations and are comfortable granting the required macOS permissions. Prefer enabling the documented safety flags, testing in a non-critical account, and limiting use to read-only tasks where possible.

If you do not need message or mail access, choose a narrower tool that does not require Full Disk Access or that separates read access from send and delete actions.

Want the same outcome, safely? Use our checked skill instead.

Source: https://github.com/griches/apple-mcp

We report what our security review found at the time we checked, with the goal of keeping people safe. Projects change; if a maintainer has since fixed this, we are glad to recheck it. Email hello@agentpod.com.

Copied to clipboard. Paste it into your AI (ChatGPT, Claude, or your agent) to add the skill.