io.github.klmlfl/case-doha-record

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Search 30,000+ decided U.S. DOHA security-clearance decisions, cited to the public record.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "case-doha-record": {
      "url": "https://www.clearancesearchengine.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (7)

• search_cases read-only

  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.

  Parameters:

  • level — string — Decision level
  • limit — integer — Max results, 1-25 (default 10)
  • query — string — Full-text search, e.g. "gambling debts sports betting"
  • outcome — string — Final outcome filter
  • year_to — integer — Latest decision year
  • guideline — string — Single guideline letter A-M (e.g. F = financial, B = foreign influence)
  • year_from — integer — Earliest decision year, e.g. 2020

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_case read-only

  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.

  Parameters:

  • case_id (required) — integer — The numeric case id from search_cases

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• similar_cases read-only

  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.

  Parameters:

  • case_id (required) — integer — The numeric case id
  • limit — integer — Max results, 1-10 (default 5)

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_statistics read-only

  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.

  Parameters:

  • by — string — Grouping (default year)
  • year_to — integer
  • guideline — string — Optional single guideline letter A-M to scope to
  • year_from — integer

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_timelines read-only

  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.

  Parameters:

  • year — integer — Optional decision year to scope to

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_conduct_recency read-only

  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.

  Parameters:

  • guideline — string — Optional single concern letter to scope to: H drugs, G alcohol, J criminal, D sexual behavior, K protected information, M IT misuse

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_candor_outcomes read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.