Verdict L402
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
사용해야 할까요
품질 및 안전성
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"verdictl402": {
"command": "npx",
"args": [
"@kechlab/verdict-mcp"
]
}
}
}실행 가능한 패키지
0.2.1stdio원격 엔드포인트
https://verdict.kechlab.com/mcpstreamable-http할 수 있는 일
도구 목록
도구 (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.
입력 스키마
{
"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.
입력 스키마
{
"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.
입력 스키마
{
"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.
입력 스키마
{
"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"
]
}커뮤니티
증거