What it does
The scanner checks MCP servers for four kinds of issue: prompt injection, credential leaks, server-side request forgery (SSRF) and tool poisoning.
It is relevant to development and security work, particularly when reviewing an MCP server before using it. The publisher's description does not say how scans are run, what results look like, or what setup is required.
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
com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
v0.3.2As shown on registry.modelcontextprotocol.io when we last read it