Is @atomicmail/mcp-modelcontextprotocol safe?
Atomic Mail MCP server — local stdio proxy with PoW auth and JMAP, for AI agents. (modelcontextprotocol install channel)
This server can change things — files, a browser, a database, or paid online services. Limit what it can reach.
Why: writes or deletes files.
What it can do
- Writes or deletes files
- Reads files
- Calls internet services
Tools it offers your AI (3):
- help
- jmap_request
- register
How to use it safely
- ✓ Point it at one project folder, never your home directory or a whole drive.
- ✓ Only give it the folders it needs; files it reads can end up in the AI’s context.
- ✓ Content it fetches from the internet can carry prompt-injection instructions.
- ✓ Pin the version (below) so an update can't change what it does without you noticing.
Code patterns worth reviewing
Automated pattern matches in the published package. Some are expected for this kind of server, and some may be false positives — they are pointers for review, not confirmed vulnerabilities.
Unsafe dynamic code execution (eval/Function)
The agent appears to evaluate dynamically constructed code (eval, new Function, or similar).
esm/_dnt.polyfills.js:113
Install it pinned
{
"mcpServers": {
"modelcontextprotocol": {
"command": "npx",
"args": ["-y", "@atomicmail/mcp-modelcontextprotocol@0.3.32"]
}
}
}Check your whole MCP setup
Agent Verify checks the servers in your Claude, Cursor and VS Code config — including whole-drive access and keys stored in plain text.
Maintain @atomicmail/mcp-modelcontextprotocol?
Show users you've thought about access: add the badge below. If something here is wrong or you've released a fix, ask for a re-scan — we update pages on request.
[](https://aimodularity.com/agentverify/mcp/atomicmail-mcp-modelcontextprotocol/)
Agent Verify reads the package published on npm as text — it is never installed or run. Ratings describe capability, not intent, and are an automated, evidence-based check, not a guarantee. Scanner 2.0.0.