PTENES
TRACK 5

🟢 MCP & Integrations

Connect Claude Code to the world: MCP servers (NotebookLM, Supabase, Firecrawl, Playwright), alternative and free models (CCR, Ollama), cloud Routines, and usage monitors.

6 modules ~50 minutes External tools
✳ Claude Code MCP client Supabase Firecrawl Playwright NotebookLM GitHub

Learning path map

Detailed content

🟢 What It Is

O MCP (Model Context Protocol) is the “USB standard” that connects Claude Code to external tools: databases, browsers, APIs, docs. Each MCP server exposes tools Claude can then use — read from Supabase, scrape a site, control the browser.

💡 Why learn

Without MCP, Claude can only see your files. With MCP, it acts in the world: queries your actual database, opens pages, and gets live data. It’s what turns the agent from a "code editor" into a "systems operator."

🔑 How to Add It and Where It Lives

claude mcp add firecrawl "npx -y firecrawl-mcp"   # adiciona um server
claude mcp list                                    # lista os configurados
/mcp                                               # painel dos servers na sessão
ScopeWhere it applies
localJust you, just this project
projectGo to .mcp.json (commit, the whole team)
userYou, across all projects

🟢 What It Is

A handful of MCP servers covers most use cases: Supabase (database), Firecrawl (scrape the web), Playwright (control the browser) and NotebookLM (knowledge base). They all come with a claude mcp add.

💡 Why learn

With Supabase MCP, Claude reads and migrates your real database without you copying the schema; with Firecrawl, it fetches content from any website; with Playwright, it tests the UI by actually clicking through it. That's productivity you can't fake with a prompt.

🔑 The Most Useful

MCPForAdd
SupabaseDatabase, auth, migrations@supabase/mcp-server-supabase
FirecrawlScrape / index websitesfirecrawl-mcp
PlaywrightBrowser, E2E testing@playwright/mcp
NotebookLMKnowledge basevia the community server
claude mcp add playwright "npx -y @playwright/mcp@latest"
claude mcp add supabase "npx -y @supabase/mcp-server-supabase" -e SUPABASE_ACCESS_TOKEN=...

Tip: after adding, run /mcp to confirm the server connected (green ✓) before asking for the task.

🟢 What It Is

Claude Code looks for the key in ANTHROPIC_API_KEY and the URL in ANTHROPIC_BASE_URL. Replace this URL with a router (CCR — claude-code-router) or a local server (Ollama), you can run it with other models — including for free.

💡 Why learn

For studying, testing, or simple tasks, you don’t need to spend expensive tokens. CCR routes requests to free or low-cost providers; Ollama runs models on your machine, offline. It keeps the Claude Code workflow and only swaps the “engine.”

🔑 The Two Routes

CCR — claude-code-router
npm install -g @musistudio/claude-code-router
ccr code        # abre o Claude Code roteado p/ outro provedor
# github.com/musistudio/claude-code-router
Ollama (local model)
ollama pull qwen2.5-coder
export ANTHROPIC_BASE_URL="http://localhost:11434"
claude   # usa o modelo local, offline

💡 When to use: local/free models are great for learning and light tasks; for serious work, official Sonnet/Opus models deliver much more. Use each where it fits.

🟢 What It Is

The Routines are automations that run in the cloud — without keeping your PC on. You define a prompt, a GitHub repository, a model, and a schedule; the trigger can be scheduling, API or GitHub event. The /loop and the scheduled tasks run locally.

💡 Why learn

It’s Claude becoming a team member who works independently: reviews PRs, updates dependencies, generates reports—on a schedule, without you. The catch: the cloud environment is stateless e can't see your .env local; secrets go in the cloud environment variables.

🔑 Local × Cloud

TypeWhere it runsDetail
RoutinesCloud (stateless)PC off · minimum cadence ~1h · requires a GitHub repo
Scheduled tasksLocal (desktop)Accesses local files
/loopLocal (session)Short intervals · doesn't survive a restart

Plan limits: Pro ~5/day · Max ~15/day · Team/Enterprise ~25/day. Each cloud run ≈ 4 vCPU / 16 GB RAM.

⚠️ Gotcha: remote routine doesn't have cookies/a session for your local browser. Automation that depends on a saved login fails — use an API or dedicated authentication, and test multiple times before “production.”

🟢 What It Is

Tools that show, in real time, how much you’re spending e what your agents are doing: token usage, cost, open sessions, and multiple terminals. The community has built several — Token-Dashboard, iccmonit, SMA (Surveil My Agents), Agent View.

💡 Why learn

Anyone running several agents in parallel (track 6) can lose track of costs and status. A monitor prevents billing surprises and shows which terminal is stuck or finished. /cost handles the basics; dashboards give you the big picture.

🔑 What Each One Covers

📊 Token-Dashboard

Token usage and cost per session/day

🖥️ iccmonit

Claude Code monitor running on the machine

🛰️ SMA — Surveil My Agents

Monitors several agents at once

🗂️ Agent View

Managing multiple terminals/threads

🟢 What It Is

Anthropic releases new versions of Sonnet e Opus frequently — Claude Code points to the latest ones. To semantic search (RAG, "second brain"), the embeddings, where models like Gemini Embedding are popular because they’re cheap/free.

💡 Why learn

Know the difference between chat model (generates code/text) and embedding model (turns text into vectors for search) avoids confusion. You can switch the first one with /model; the second one feeds your RAG (track 6).

🔑 Chat × Embedding

TypeDoesExamples
Chat / codeReasons, edits, chatsOpus · Sonnet · Haiku
EmbeddingVectorizes text for searchGemini Embedding 2.0
/model         # ver e trocar o modelo de chat ativo
/model sonnet  # último Sonnet (dia-a-dia)
/model opus    # último Opus (tarefas difíceis)
← T4 Skills Next: T6 Agents & Cowork →