← Back to MCP setup
🔬

Deep research

dbn.deep_research

Expand a legal question into research angles and synthesize a cited brief.

Parameter Type Required Description
query string Legal question to research in depth.
paste_text string Supporting document text to research from.
language string
en | no | uk | pl | auto
Response language: en, no, uk, pl, or auto.
use_case_context boolean Include context from your Case Workbench session (true/false).

* Purple = required

POST /api/mcp/user/tools/dbn.deep_research/invoke

{
  "query": "ECHR Article 8 violations in Norwegian child welfare cases",
  "language": "en",
  "use_case_context": false
}
{
  "ok": true,
  "research_angles": [
    "Procedural safeguards under ECHR Art. 6 in child welfare proceedings",
    "Substantive requirements for care order threshold (BVL §4-12)",
    "Norwegian Supreme Court interpretation of best interests standard"
  ],
  "brief": "Research synthesis: The European Court of Human Rights has found Norway in violation of Art. 8 in 14 cases since 2015, with the core issue being...",
  "citations": [
    "Strand Lobben m.fl. mot Norge, EMD-37283/13 (10.09.2019)",
    "Johansen mot Norge, EMD-17383/90 (07.08.1996)"
  ],
  "credits_used": 15
}

Create your MCP token on the setup page and use it with any supported client.

Set up MCP →
Process-and-forget by default. All tool calls process your text in memory and return results to your AI client. Nothing is saved to My Case unless you explicitly call dbn.save_to_case.

Tools provide legal preparation support, not final legal advice. Results are for informational purposes and should be reviewed by a qualified legal professional.