Verdict L402
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"verdictl402": {
"command": "npx",
"args": [
"@kechlab/verdict-mcp"
]
}
}
}可运行的软件包
0.2.1stdio远程端点
https://verdict.kechlab.com/mcpstreamable-http它能做什么
工具清单
工具（4）
🟢verdict_guard(text)
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.
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The untrusted text to examine (4000 characters maximum in free samples)."
}
},
"required": [
"text"
]
}🟢verdict_command_gate(command, intent)
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.
输入模式
{
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The shell command the agent wants to run."
},
"intent": {
"type": "string",
"description": "Optional. What the human asked the agent to do."
}
},
"required": [
"command"
]
}⚪verdict_mcp_vet(name, description, tools, permissions)
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.
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Name of the tool or server."
},
"description": {
"type": "string",
"description": "The description text it exposes to the agent."
},
"tools": {
"type": "array",
"description": "Optional list of { name, description } of the functions it exposes.",
"items": {
"type": "object"
}
},
"permissions": {
"type": "array",
"description": "Optional permissions requested, for example filesystem:write, network, shell.",
"items": {
"type": "string"
}
}
},
"required": [
"name",
"description"
]
}🟢verdict_firewall(goal, content, action)
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.
输入模式
{
"type": "object",
"properties": {
"goal": {
"type": "string",
"description": "The objective the human gave."
},
"content": {
"type": "string",
"description": "The untrusted content the agent read."
},
"action": {
"type": "string",
"description": "The action the agent wants to run (tool call, command, payment)."
}
},
"required": [
"goal",
"content",
"action"
]
}社区
证据