Dataset-listing granularity audit
Per-dataset granularity verdicts keyed to the dataset's own manifest hash, before you pay.
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
~214token 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 0.17%)
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": {
"dataset-listing-granularity-audit": {
"url": "https://textforagents.com/products/dataset-listing-granularity-audit/mcp"
}
}
}远程端点
https://textforagents.com/products/dataset-listing-granularity-audit/mcpstreamable-http它能做什么
工具清单
工具(3)
🟢 只读🟡 写入🔴 删除⚪ 未知
⚪audit_listing(listing, siblings, listing_url)
Full dataset audit of a listing ($0.04 after the one-time free trial, or pass). Args: listing, siblings (or listing_url).
输入模式
{
"type": "object",
"properties": {
"listing": {
"type": "object"
},
"siblings": {
"type": "array"
},
"listing_url": {
"type": "string"
}
},
"required": []
}🟡query_verdict(dataset_id, manifest_hash, shared_line_hash)
Precomputed signed verdict for a dataset ($0.01). Args: dataset_id, optional manifest_hash + shared_line_hash for manifest-change-trigger checking.
输入模式
{
"type": "object",
"properties": {
"dataset_id": {
"type": "string"
},
"manifest_hash": {
"type": "string"
},
"shared_line_hash": {
"type": "string"
}
},
"required": [
"dataset_id"
]
}⚪verify_verdict(signed_verdict)
Verify an Ed25519-signed verdict (free). Args: signed_verdict.
输入模式
{
"type": "object",
"properties": {
"signed_verdict": {
"type": "object"
}
},
"required": [
"signed_verdict"
]
}社区
证据
最近观测
已验证未记录版本3 个工具