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

notion_mcp: why it is not safe to use

Our review did not identify security or privacy issues in notion_mcp; it passed based on a limited, readable Notion-only task update scope.

What we found

Our review of `notion_mcp` did not find issues that would block use under our security and privacy checks. The repository is short and readable, with no encoded or hidden payloads, and we did not find hidden instructions in the README or source. The tool scope is narrow: it creates tasks and marks tasks complete in a user-connected Notion database.

We found no hardcoded secrets. The code expects `NOTION_API_KEY` and `NOTION_DATABASE_ID` from a local `.env` file, and `.env` is gitignored. Network activity appears limited to ordinary HTTPS calls to the configured Notion API for the connected database. We did not see evidence of remote code fetching, unrelated credential access, privilege changes, or delete functionality.

This is a point-in-time review of the current repository state and described behavior.

What to do instead

If you use this skill, keep the connected Notion integration scoped only to the database it needs, store the API key locally, and review requested actions before running them. If you need broader workspace automation, apply the same checks to any additional skills or integrations before enabling them.

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

Source: https://github.com/danhilse/notion_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.