Agent Access Door Check
Before your agent sets out, ask whether the site will let it in
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~356token 数（工具定义）
~391 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.28%）
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": {
"agent-access-door-check": {
"url": "https://textforagents.com/products/agent-access-door-check/mcp"
}
}
}远程端点
https://textforagents.com/products/agent-access-door-check/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢door_check(site, task, is_partner, evidence, today)
Pre-flight per-site x per-task access verdict: PERMITTED / LICENSED-ONLY / PARTNER-ONLY / POLICY-BLOCKED / COLLATERAL-BLOCKED / UNKNOWN with evidence + route. $0.05/call x402 (X-PAYMENT header), one free per operator ever, plan covers cached + 200 fresh/mo.
输入模式
{
"type": "object",
"properties": {
"site": {
"type": "string"
},
"task": {
"type": "string"
},
"is_partner": {
"type": "boolean"
},
"evidence": {
"type": "object"
},
"today": {
"type": "string"
}
},
"required": [
"site",
"task"
]
}🟡assemble_evidence(site, task, evidence)
Submit a validated evidence doc for fresh assembly (no verdict returned).
输入模式
{
"type": "object",
"properties": {
"site": {
"type": "string"
},
"task": {
"type": "string"
},
"evidence": {
"type": "object"
}
},
"required": [
"site",
"task",
"evidence"
]
}⚪watch_register(site, task)
Watch a site x task; alert on class change.
输入模式
{
"type": "object",
"properties": {
"site": {
"type": "string"
},
"task": {
"type": "string"
}
},
"required": [
"site",
"task"
]
}⚪collateral_report(site, task)
Site-facing collateral report for a COLLATERAL-BLOCKED verdict.
输入模式
{
"type": "object",
"properties": {
"site": {
"type": "string"
},
"task": {
"type": "string"
}
},
"required": [
"site",
"task"
]
}🟢get_receipt(receipt_id)
Fetch a stored verdict receipt by id.
输入模式
{
"type": "object",
"properties": {
"receipt_id": {
"type": "string"
}
},
"required": [
"receipt_id"
]
}社区
证据
最近观测
已验证未记录版本5 个工具