What it does
The server scans code for hardcoded secrets, with the publisher naming AWS, Stripe, GitHub and JWT credentials as covered types. Its stated point of use is before an AI agent commits code, so exposed credentials can be caught at that step.
The available source does not describe installation steps, setup requirements or configuration details.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.vladimirbakalov/secretguard-mcp
Scans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it.
v0.1.4As shown on registry.modelcontextprotocol.io when we last read it