Skip to content

Verdict L402

by jeannicolasdavid1979 · remote · local (npm) · no sign-in to list tools · v0.2.2 · published by GitHub user jeannicolasdavid1979

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

Changes · 4
CompareRegistry entry

4 tools: 4 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 4Claude Code: ask
  • verdict_command_gateFree sample.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.command), which can change anything it can reach.
    Description, as the server wrote it
    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_firewallFree sample.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • verdict_guardFree sample.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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 action: use verdict_firewall.
  • verdict_mcp_vetFree sample.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.2.2. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__verdictl402__verdict_guard",
      "mcp__verdictl402__verdict_command_gate",
      "mcp__verdictl402__verdict_mcp_vet",
      "mcp__verdictl402__verdict_firewall"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as verdictl402. Review it before you use it.