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

Google Photos MCP Server: why it is not safe to use

We found expected OAuth token storage and access to a private Google Photos library, which merits caution before connecting personal accounts.

What we found

Our review did not find hidden prompts, hardcoded secrets, undisclosed remote code execution, or destructive actions. The code appears to do what it says: connect to Google Photos and Google Photos Picker APIs to create albums, upload media, add enrichments, and set covers for the connected account.

The reason for the warning is narrower. This skill reads Google OAuth client credentials from environment variables and stores access and refresh tokens after authentication. That is consistent with how this type of integration works, but it also means the skill can reach a private Google Photos library and keep persistent tokens locally on the system where it runs. For a photo library, that has privacy implications even when the implementation matches the stated purpose.

What to do instead

Use this skill only with an account and device you trust. Prefer a separate Google account or a limited test library rather than a primary personal archive. Store OAuth credentials and token files in a protected location, rotate them if exposure is suspected, and disconnect the app in your Google account when you no longer need access. Review the scopes and local storage setup before use.

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

Source: https://github.com/savethepolarbears/google-photos-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.