Blocker-aware decision layer for AI coding agents, grounded in source-linked, time-sensitive facts.
Model Context Protocol (MCP) Server: PocketLantern
PocketLantern (io.github.pocketlantern/pocketlantern) is an MCP server that provides a blocker-aware decision layer for AI coding agents. Its description emphasizes source-linked, time-sensitive facts. The package is referenced with npm, CI, and MIT license badges, indicating an actively maintained project.
Your AI agent sounds confident. It missed the blockers.
Prices shift, versions break, licenses change. PocketLantern is a blocker-aware decision layer for AI coding agents, grounded in source-linked, time-sensitive facts.
Try these queries
Ask your AI agent after installing PocketLantern:
"Which auth provider — Clerk, Auth0, or Cognito?"
code
⚠️ Cognito password hashes are permanently non-exportable
⚠️ Auth0 password export requires support ticket — Free tier excluded
⚠️ Auth0 Rules/Hooks EOL 2026-11-18 — Actions not portable
✅ Clerk has the most flexible migration path
"Should I upgrade to Next.js 16?"
code
⚠️ Sync API access fully removed — all dynamic calls must be awaited
⚠️ Custom webpack config breaks next build
⚠️ next lint removed — switch to Biome or ESLint CLI
⚠️ Requires Node.js 20.9.0+, TypeScript 5.1.0+, React 19.0+
✅ Plan phased migration — codemod doesn't cover webpack or middleware
"Can I use the OpenAI Realtime API?"
code
⚠️ gpt-4o-realtime-preview removed 2026-05-07
⚠️ Beta interface (realtime=v1 header) removed same date
⚠️ GA event schema incompatible — 4 event renames
✅ Start on GA from day one — or plan dual-stack migration
Three questions. Three blocker types. Same AI, different facts.
PocketLantern demo — Node.js 20→24 upgrade blockers surfaced in seconds
init registers the MCP server in ~/.claude.json and adds a one-line rule to your project's CLAUDE.md. Restart Claude Code (Ctrl+C, then run claude again), then ask your first query.
Cursor / Windsurf / other MCP clients
Add to your MCP config (Cursor: ~/.cursor/mcp.json):
Then add this line to your project rules (.cursorrules, Kiro steering file, etc.):
code
For technology decisions, upgrades, migrations, or licensing questions: before finalizing your answer, check the PocketLantern MCP server's search_cards tool for blockers in these bundled decision cards — your training data may be stale.
"How did Vercel pricing change with Fluid Compute?"
Billing split to Active CPU + Memory, shared-process concurrency breaks isolation
"Prisma or Drizzle for Edge/serverless?"
Prisma v7 ESM + driver adapter breaking, Edge preview-only; Drizzle 0.30-1.0 also breaking
Verify installation
bash
pocketlantern doctor # check installation status
pocketlantern search "auth pricing"# search cards from CLI
How it works
PocketLantern is an MCP server. Your AI agent calls search_cards — and gets source-linked decision cards plus source-linked blocker warnings where available.
Local cardset. Instant lookup. No vector database. No embeddings. Keyword search, card links, and source-linked blocker warnings where available. The value is in source-linked decision cards, not clever retrieval alone.
code
search_cards("auth", constraints:["serverless"]) -> cards + blockers
get_card("auth/clerk-vs-auth0-vs-cognito-2026") -> full card with facts
get_related_cards(...) -> connected topics
What's included
Blocker-aware decision cards across 27 categories — plus source-linked blocker warnings from the bundled graph index. Ships with the npm package, works immediately, no network, no account:
