Repo · Safety & guardrails

Jev Shield

Check MCP calls, outputs, and tool descriptions.

Open github.com ↗

From the repository

Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

ai-safetymcpprompt-injectionsecurityvercel-ai-gateway

How builders describe it

Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

Semantic MCP firewall and agent skill: screens tool calls, tool results, and tool descriptions with TypeSafe Jev via Vercel AI Gateway experimental_evaluate.

The decision Jev makes

Allow, flag or escalate a message, tool call or action.

Where it fits

Screening messages, tool calls and outputs before they cause trouble. Jev gives a fast, calibrated verdict that can sit in front of every request or agent action. All 131 safety & guardrails projects →

Related projects