Is axm.sh safe?
Extension manager for AI coding agents — install skills, subagents, MCP servers, rules, hooks, knowledge, and packs across Claude Code, Codex, Cursor, Copilot, and more.
If an AI agent using this server were tricked, the damage it could do through this server is limited.
Why: no high-reach capabilities found.
What it can do
No commands, file changes, browser control or database access found in its code.
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.
Command injection risk
The agent appears to pass input into a shell or command execution path.
dist/src/runtime.js:47
Plaintext HTTP endpoint
A non-localhost endpoint is referenced over plain HTTP instead of HTTPS.
dist/src/cli-reference.js:94
Install it pinned
{
"mcpServers": {
"axm.sh": {
"command": "npx",
"args": ["-y", "axm.sh@0.51.0"]
}
}
}Source · npm · FSL-1.1-MIT license · 975 downloads last week
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 axm.sh?
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/axm-sh/)
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.