Lab 087: Copilot + MCP: GitHub, Playwright, and Your Own Server¶
Free-first design
Complete the guided exercise with Copilot Free or the included simulation. Paid features are optional and explicitly labeled.
AI Credit impact
Low for guided work; medium/high for agentic or repeated runs. Prefer automatic model selection, plan before acting, keep context focused, and avoid unnecessary parallel sessions.
What You'll Learn¶
- Connect approved MCP tools to Copilot
- Compare GitHub, Playwright, and local custom servers
- Apply allowlists and read-only tool hints
- Design a minimal tool contract
GH-300 alignment¶
Use Copilot features (25–30%) · Data and architecture (10–15%). This mapping follows the GH-300 curriculum snapshot dated 2026-08-07. The official outline may retain older product wording such as “Copilot Edits”; this lab teaches the current product experience and calls out that difference.
Concept Map¶
flowchart LR
C[Copilot client] --> G[GitHub MCP: repository data]
C --> P[Playwright MCP: localhost UI]
C --> O[OutdoorGear MCP: local tool]
G --> A[Approval + allowlist]
P --> A
O --> A
Hands-on Exercise¶
Step 1: Inventory the servers¶
List each server, transport, credentials, data boundary, and tool names before connecting it. Prefer the GitHub MCP Registry or a server you can inspect.
Step 2: Run a read-only GitHub task¶
Ask Copilot to list issues or inspect repository metadata without changing state. Confirm every tool invocation before expanding permissions.
Step 3: Run a local Playwright check¶
Use Playwright MCP only against localhost. Capture an accessibility observation and never send private production data to an unreviewed server.
Step 4: Reuse Lab 020¶
Expose one local OutdoorGear lookup tool from Lab 020. Add a strict schema, bounded output, explicit errors, and an allowlist.
Supporting kit¶
The site build generates stable PDF and ZIP downloads. The ZIP contains the lab guide and every supporting file declared for this lab.