case-doha-record
Search 30,000+ decided U.S. DOHA security-clearance decisions, cited to the public record.
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": {
"case-doha-record": {
"url": "https://www.clearancesearchengine.com/api/mcp"
}
}
}远程端点
https://www.clearancesearchengine.com/api/mcpstreamable-http它能做什么
工具清单
工具(7)
🟢search_cases(query, guideline, outcome, level, year_from, ...)
Search 30,000+ decided public DOHA security-clearance decisions (1996 to present). Full-text query plus filters. Returns matching cases with outcome, date, guidelines, and a citable URL each.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Full-text search, e.g. \"gambling debts sports betting\""
},
"guideline": {
"type": "string",
"description": "Single guideline letter A-M (e.g. F = financial, B = foreign influence)"
},
"outcome": {
"type": "string",
"enum": [
"granted",
"denied"
],
"description": "Final outcome filter"
},
"level": {
"type": "string",
"enum": [
"hearing",
"appeal"
],
"description": "Decision level"
},
"year_from": {
"type": "integer",
"description": "Earliest decision year, e.g. 2020"
},
"year_to": {
"type": "integer",
"description": "Latest decision year"
},
"limit": {
"type": "integer",
"description": "Max results, 1-25 (default 10)"
}
}
}🟢get_case(case_id)
Fetch one decided DOHA case in full: what was alleged, the judge's findings per allegation, per-guideline formal findings, outcome, judge, representation, and appeal history. Use case_id from search_cases.
输入模式
{
"type": "object",
"properties": {
"case_id": {
"type": "integer",
"description": "The numeric case id from search_cases"
}
},
"required": [
"case_id"
]
}🟢similar_cases(case_id, limit)
The most similar decided cases to a given case, ranked by how alike the ALLEGATIONS read (never by outcome). Same list shown on the case page.
输入模式
{
"type": "object",
"properties": {
"case_id": {
"type": "integer",
"description": "The numeric case id"
},
"limit": {
"type": "integer",
"description": "Max results, 1-10 (default 5)"
}
},
"required": [
"case_id"
]
}🟢get_statistics(by, guideline, year_from, year_to)
Grant/denial statistics over decided hearing-level DOHA cases, grouped by year or by guideline, always with sample sizes. Same population rules as the site's Insights page.
输入模式
{
"type": "object",
"properties": {
"by": {
"type": "string",
"enum": [
"year",
"guideline"
],
"description": "Grouping (default year)"
},
"guideline": {
"type": "string",
"description": "Optional single guideline letter A-M to scope to"
},
"year_from": {
"type": "integer"
},
"year_to": {
"type": "integer"
}
}
}🟢get_timelines(year)
Measured DOHA timelines: median days from Statement of Reasons to hearing and to decision, from dates stated in the decisions themselves. Optionally scoped to one decision year.
输入模式
{
"type": "object",
"properties": {
"year": {
"type": "integer",
"description": "Optional decision year to scope to"
}
}
}🟢get_conduct_recency(guideline)
How much time had passed between the most recent conduct and the decision, measured from dates stated in the decisions, for the incident-type concerns (drugs, alcohol, criminal conduct, sexual behavior, protected information, IT misuse). Reports median years before favorable vs unfavorable decisions, with counts. Descriptive association, never a prediction.
输入模式
{
"type": "object",
"properties": {
"guideline": {
"type": "string",
"description": "Optional single concern letter to scope to: H drugs, G alcohol, J criminal, D sexual behavior, K protected information, M IT misuse"
}
}
}🟢get_candor_outcomes
How cases with a candor allegation (falsification, omission, or lack of candor) were resolved in the decided record: the favorable rate with vs without such an allegation, when the judge found a deliberate falsification vs when the applicant rebutted it, and when the applicant corrected the record before being confronted. Counts and denominators throughout. Descriptive, never a prediction.
输入模式
{
"type": "object",
"properties": {}
}社区
证据