Configuration

DeepPlan MCP is configured via environment variables in a .env file or your MCP server config.

Environment Variables

VariableDefaultDescription
OPENROUTER_API_KEY(required)Your OpenRouter API key
OPENROUTER_MODELanthropic/claude-sonnet-4Fallback model for single-call mode
COUNCIL_MODELminimax/minimax-m2.5Model used for the 4 expert personas
LEAD_ARCHITECT_MODEL(same as COUNCIL_MODEL)Model used for the Lead Architect synthesis
DRAFT_PLAN_MAX_LENGTH8000Maximum characters for input draft plan

Model Selection

Expert Personas (4 parallel calls)

The expert personas (Security, Performance, UX/DX, DevOps) use COUNCIL_MODEL. We recommend a fast, cost-effective model since these run in parallel:

  • Recommended: minimax/minimax-m2.5 — fast, affordable, good analysis
  • Alternative: google/gemini-2.0-flash — slightly more expensive, broader knowledge

Lead Architect (1 synthesis call)

The Lead Architect uses LEAD_ARCHITECT_MODEL. This should be a stronger model capable of synthesizing multiple reports:

  • Recommended: google/gemini-3-flash-preview — excellent synthesis, fast
  • Alternative: anthropic/claude-sonnet-4 — highest quality, slower

Tool Parameters

When calling upgrade_architecture_blueprint from your IDE:

ParameterRequiredDescription
draft_planYesYour architecture plan text
tech_stackNoe.g. “SvelteKit, Cloudflare Workers, D1”
model_choiceNoOverride Lead Architect model for this call
context_constraintsNoe.g. “Must run on Edge Runtime”

Performance Tips

  1. Keep draft plans concise — 200-500 words is ideal
  2. Specify tech stack — enables stack-specific recommendations
  3. Add constraints — prevents incompatible suggestions