All servers · Build & deploy

Verdict L402

io.github.jeannicolasdavid1979/verdictl402 · v0.2.2

Measured by MCP Station

Instruction-like text was found in verdict_command_gate, verdict_guard. This is a pattern match, not a verdict. What we look for

Description written by the publisher, not verified

Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.

Connect

claude mcp add --transport http verdictl402 https://verdict.kechlab.com/mcp

{
  "mcpServers": {
    "verdictl402": {
      "url": "https://verdict.kechlab.com/mcp"
    }
  }
}

Tools as reported by the server

• verdict_guard
  Free sample. Before your agent reads untrusted text (web page, email, document, tool output), check it for prompt injection, data exfiltration requests, secrets and toxic content. Returns allow, review or block with scores and reasons. Use it on text you did not write. Do not use it to judge an acti
• verdict_command_gate
  Free sample. Before a coding agent runs a shell command, ask whether to allow, review or block it: root deletion, download and run, privilege escalation, secret exfiltration. Pass the human intent when you know it. Not a sandbox: it reads the command, it does not run it.
• verdict_mcp_vet
  Free sample. Before installing an MCP server, skill or tool: is its description poisoned (hidden orders to the agent, excessive permissions, look-alike names)? Returns allow, review or block with reasons.
• verdict_firewall
  Free sample. Before an agent acts on untrusted content (pay, send, delete, click, reply), give the human goal, the content it read and the action it proposes. Returns allow, review or block: it catches actions that follow orders hidden in the content.

Website · JSON · Text for agents · Registry updated 2026-10-20