io.github.jeannicolasdavid1979/verdictl402

up checked 2026-11-11T06:37:31.268Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Verdict L402

Publisher-provided description

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

Summary by lookupd

Screens shell commands, untrusted text, MCP tools and ERC-20 contracts for risk before an agent acts; returns allow, review or block.

Install

Claude Code, remote (streamable-http)

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

Claude Code, npm package (stdio)

claude mcp add verdictl402 -- npx -y @kechlab/verdict-mcp

Codex, remote (streamable-http)

codex mcp add verdictl402 --url https://verdict.kechlab.com/mcp

Codex, npm package (stdio)

codex mcp add verdictl402 -- npx -y @kechlab/verdict-mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "verdictl402": {
      "command": "npx",
      "args": [
        "-y",
        "@kechlab/verdict-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (5 tools)

Publisher-provided text

• 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
• 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
• 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)?
• verdict_token_check Free sample. Before your agent buys or swaps an ERC-20 token on Base: static reading of its contract. Returns allow, review or block with facts: is it a contrac
• 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. R

Details

• Version: 0.2.2
• Transports: streamable-http, stdio
• Uptime (7 days): 100%
• Median latency: 819 ms
• First indexed: 2026-11-01T09:35:53.735Z
• Last seen in registry: 2026-11-01T09:35:53.866Z
• Website: https://verdict.kechlab.com

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.jeannicolasdavid1979/verdictl402.svg)](https://lookupd.com/servers/io.github.jeannicolasdavid1979/verdictl402)

• 62141 servers
• Last crawl: 2026-11-11T18:39:04.612Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp