What it does
According to the publisher, Verdict lets an agent ask whether a planned action is safe before it runs. The description names injection, shell commands and MCP installs as the kinds of actions it covers. The listing does not describe how verdicts are produced.
The publisher's description suggests it fits workflows where an agent runs shell commands, installs MCP servers, or handles input that could carry injected instructions, and where a check before execution is wanted. The source gives no details on setup or running requirements.
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
Verdict
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
v0.2.0As shown on registry.modelcontextprotocol.io when we last read it