refactor(docs): add tutorials overview & mimic/Jupyter tutorial

Author: simonprovost

docs/stylesheets/extra.css

@@ -128,4 +128,3 @@
   border-color: var(--md-primary-fg-color, #6200ee);
   box-shadow: 0 2px 6px rgba(0, 0, 0, 0.12);
 }
-

docs/stylesheets/extra_mkdocs.css

@@ -15,4 +15,4 @@
 
 .md-typeset h1 {
     margin: 0 0 0.1em;
-}
+}

docs/tutorials/index.md

@@ -0,0 +1,58 @@
+# 📚 Tutorials Hub
+# 📚 Tutorials Hub
+
+Hey there, let's explore the **MCPStack Tutorials**!
+
+Here you’ll find guided, hands-on walkthroughs showing how to build, run, and extend pipelines.
+
+<div class="grid cards" markdown>
+
+-   :fontawesome-solid-triangle-circle-square:{ .lg .middle } __Build your first pipeline__
+    {: data-tutorials-card data-filter="pipeline getting started intro"}
+
+    ---
+
+    Learn how to create your first pipeline from scratch.
+
+    [:octicons-arrow-right-24: Start Tutorial](first-pipeline.md)
+
+-   :material-content-save:{ .lg .middle } __Saving & Loading Pipelines__
+    {: data-tutorials-card data-filter="save load persist pipelines"}
+
+    ---
+
+    How to persist and reload pipelines for reproducibility.
+
+    [:octicons-arrow-right-24: Start Tutorial](save-load.md)
+
+-   :material-wrench:{ .lg .middle } __Writing your first Tool__
+    {: data-tutorials-card data-filter="custom tool development"}
+
+    ---
+
+    Build and register your own MCP tool.
+
+    [:octicons-arrow-right-24: Start Tutorial](first-tool.md)
+
+-   :material-tune:{ .lg .middle } __Creating a Preset__
+    {: data-tutorials-card data-filter="preset pipelines reproducibility"}
+
+    ---
+
+    Package pre-wired pipelines for reuse.
+
+    [:octicons-arrow-right-24: Start Tutorial](first-preset.md)
+
+-   :material-table:{ .lg .middle } __MIMIC + Jupyter Pipeline__
+    {: data-tutorials-card data-filter="MIMIC Jupyter conversational AI reproducible analysis"}
+
+    ---
+
+    NEW! A walkthrough of stacking the **MIMIC MCP** with the **Jupyter MCP**
+
+    [:octicons-arrow-right-24: Watch & Learn](mimic-jupyter.md)
+
+</div>
+
+!!! tip
+    This page will expand as more tutorials are added — contributions welcome!

docs/tutorials/mimic-jupyter.md

@@ -0,0 +1,67 @@
+# 🧪 Tutorial: MIMIC + Jupyter Pipeline
+# 🧪 Tutorial: MIMIC + Jupyter Pipeline
+
+This tutorial shows how to **stack two MCPs**:
+
+- **MIMIC** (conversational AI on the MIMIC-IV clinical database)
+- **Jupyter** (reproducible notebook analysis)
+
+You’ll learn how to:
+
+1. Build a pipeline with both tools
+2. Ask natural language questions over MIMIC-IV
+3. Export results into a Jupyter Notebook for reproducible Python analysis
+
+---
+
+## 🎥 Video Walkthrough
+
+<iframe width="860" height="515" src="https://www.youtube.com/embed/uTjIbN0GSHU?si=4rwoYmX32y9Cs6vs" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
+
+---
+
+## 🔧 Step 1 — Build with Pipeline W/ MIMIC Default
+
+MIMIC Default is basically using the default MIMIC-IV demo database.
+
+```bash
+uv run mcpstack pipeline mimic --new-pipeline my_pipeline.json
+```
+
+## 🔧 Step 2 — Create a Jupyter `ToolConfig`
+
+Basically, Jupyter MCP works with some sort of connections between the LLM and the Jupyter instance. This is via a
+URL and a TOKEN. Hence, the need for a `ToolConfig`.
+
+```bash
+uv run mcpstack tools jupyter configure \
+    --token YOUR_JUPYTER_TOKEN
+
+# This create a `jupyter_config.json` file
+```
+
+## 🔧 Step 3 — Add To The Tool To The Pipeline
+
+```bash
+uv run mcpstack pipeline mimic --to-pipeline my_pipeline.json --tool-config jupyter_config.json
+```
+
+## 🔧 Step 4 — Compose & Run the Pipeline On Claude Desktop
+
+```bash
+uv run mcpstack build --pipeline my_pipeline.json --config-type claude
+```
+
+Now you can ask the LLM to operate the MIMIC tool and export results into Jupyter.
+
+## 📣 Prompt Used During The Demo Video
+
+```text
+Hey there! May you extract 50 patients from MIMIC-IV and do a quick reproducible analysis of the data with pandas
+for me please?
+
+If you need to add packages, `!uv add <package_name>`.
+```
+
+!!! tip
+    Try chaining additional tools (e.g., scikit-longitudinal) to build research-ready clinical workflows.

mkdocs.yml

@@ -161,10 +161,12 @@ nav:
           - MCP Hosts & Config Generators: guides/concepts/mcp-hosts-and-configs.md
   - MCPs Marketplace: mcp_marketplace.md
   - Tutorials:
+      - Overview: tutorials/index.md
       - Build your first pipeline: tutorials/first-pipeline.md
       - Saving & Loading Pipelines: tutorials/save-load.md
       - Writing your first Tool: tutorials/first-tool.md
       - Creating a Preset: tutorials/first-preset.md
+      - MIMIC + Jupyter Pipeline: tutorials/mimic-jupyter.md
   - API Reference:
       - MCPStack Core:
           - MCPStackCore: API/mcpstackcore.md