Setup: the servers ship in eic-shell — drop the clone/PATH/bootstrap steps

[aprozo]

Setup: ./eic-shell → eic-mcp up → eic-mcp config opencode; assistant inside eic-shell or on your machine; macOS: DOCKER_OPTIONS="$(./eic-shell -- eic-mcp docker-args)" (eic/eic-shell#39). Draft until eic_xl includes the servers (eic/containers#357).

[github-actions]

Thank you!

Thank you for your pull request 😃

🤖 This automated message can help you check the rendered files in your submission for clarity. If you have any questions, please feel free to open an issue in {sandpaper}.

If you have files that automatically render output (e.g. R Markdown), then you should check for the following:

• 🎯 correct output
• 🖼️ correct figures
• ❓ new warnings
• ‼️ new errors

Rendered Changes

🔍 Inspect the changes: https://github.com/eic/tutorial-mcp/compare/md-outputs..md-outputs-PR-1

The following changes were observed in the rendered markdown documents:

 01-why-genai-for-physics.md   | 175 +++++++++++------------------
 02-your-ai-coding-setup.md    |  28 ++---
 03-mcp-servers.md             | 249 ++++++++++--------------------------------
 04-skills.md                  |  91 +++++----------
 05-end-to-end-agents.md       |  81 ++++++--------
 06-eic-mcp-servers.md         | 111 +++++--------------
 about-the-physics.md (gone)   | 128 ----------------------
 analysis-approaches.md (gone) |  82 --------------
 config.yaml                   |   3 -
 discuss.md (gone)             |  30 -----
 index.md                      |   8 +-
 instructor-notes.md           |  40 +++----
 md5sum.txt                    |  23 ++--
 setup.md                      | 159 +++++++++------------------
 14 files changed, 298 insertions(+), 910 deletions(-)

What does this mean?

If you have source files that require output and figures to be generated (e.g. R Markdown), then it is important to make sure the generated figures and output are reproducible.

This output provides a way for you to inspect the output in a diff-friendly manner so that it's easy to see the changes that occur due to new software versions or randomisation.

⏱️ Updated at 2026-09-30 14:04:00 +0000

[Copilot]

Copilot review overview

🟡 Changes recommended

The setup contains two broken directory/context instructions and does not implement the advertised macOS workflow.

Review effort: Balanced
Findings: 3

Open (3)

• Run recovery upgrade outside eic-shell from launcher directory · New
• Avoid permanently patching launcher; use transient DOCKER_OPTIONS · New
• Download opencode config into the analysis working directory · New

What changed in this PR

Simplifies the tutorial now that eic-shell ships the MCP servers and opencode.

Changes:

• Removes cloning, PATH, and server bootstrap steps.
• Streamlines setup and lesson text.
• Removes redundant reference pages and bundled launcher.

File	Description
README.md	Simplifies setup and repository overview
learners/​setup.md	Reworks eic-shell and assistant setup
learners/​discuss.md	Removes discussion page
learners/​analysis-approaches.md	Removes alternative-analysis page
learners/​about-the-physics.md	Removes physics reference page
instructors/​instructor-notes.md	Updates workshop preparation
index.md	Refines introductory wording
files/​skills/​AGENTS.md	Clarifies no-download policy
files/​mcp-config/​vscode-mcp.json	Updates server-start guidance
files/​mcp-config/​opencode.jsonc	Shortens configuration comments
files/​mcp-config/​copilot-mcp-config.json	Updates server-start guidance
extras/​README.md	Removes deleted-page reference
episodes/​06-eic-mcp-servers.md	Condenses the server catalog
episodes/​05-end-to-end-agents.md	Replaces cloned resources with downloads
episodes/​04-skills.md	Updates skill installation workflow
episodes/​03-mcp-servers.md	Simplifies MCP setup and explanations
episodes/​02-your-ai-coding-setup.md	Streamlines physics setup
episodes/​01-why-genai-for-physics.md	Condenses agent concepts
config.yaml	Removes deleted learner pages
bin/​eic-mcp	Removes the bundled launcher

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.