agent-scan

MCP Server

Security scanner for AI agents, MCP servers and agent skills.

Copy the install, test the workflow, then decide if it earns a permanent slot.

2,287

Why nowMoving now

Fresh repo activity plus visible builder pull. This is the kind of tool people test before it turns obvious.

DecisionHigh-conviction move

Copy the install, test the workflow, then decide if it earns a permanent slot.

Trial costFast eval

You can test this quickly and remove it cleanly if it misses.

Risk35/100

GitHub health 50/100. no security policy. 20 open issues make this testable, but not something to trust blind.

What You Are Adopting

AI Agent

Universal

Model

Multiple

Build Time

Minutes

One command inClean rollbackLow commitment

RegistryAdds a named entry to Claude config. One command to remove.

Fastest way to find out if agent-scan belongs in your setup.

Copy the install command, run a real test, and back it out cleanly if it slows you down.

Try now

claude mcp add agent-scan -- npx agent-scan

Run this first. You will know quickly if the workflow earns a permanent slot.

Back out

claude mcp remove agent-scan

No messy cleanup loop. If it misses, remove it and keep moving.

Install Location

~/  └─ .claude.json    └─ mcp_servers/      └─ agent-scan ← registers here

Security scanner for AI agents, MCP servers and agent skills.. An open-source mcp server for the AI coding ecosystem.

ActiveLast commit today

20open issues

Submitted March 18, 2026