learning_ai_common_plat/services/mcp-server/.env.example
saravanakumardb1 027e2163a0 feat(mcp-server): scaffold @bytelyst/mcp-server on port 4006 with 10 tools across 4 namespaces
- platform.telemetry.{query,clusters,metrics}
- platform.diagnostics.sessions.{list,create,get,update,getLogs,getTraces}
- extraction.{run,models,cacheStats}
- support.createDebugPack (compound: clusters + optional diag session + markdown summary)
- Role-gated (viewer/admin/super_admin), JWT auth via platform-service secret
- Proxies to platform-service:4003 and extraction-service:4005
- 4 Vitest tests passing, tsc --noEmit clean
2026-03-05 11:47:08 -08:00

15 lines
346 B
Plaintext

# MCP Server — port 4006
PORT=4006
HOST=0.0.0.0
LOG_LEVEL=info
# Upstream services
PLATFORM_SERVICE_URL=http://localhost:4003
EXTRACTION_SERVICE_URL=http://localhost:4005
# Auth — same JWT_SECRET as platform-service (tokens issued there are validated here)
JWT_SECRET=change-me-in-production
# Optional: AKV resolution
AZURE_KEYVAULT_URL=