Merge pull request #88 from MarcSkovMadsen/enhancement/holoviews_mcp_server

Simplify getting started

Author: MarcSkovMadsen

README.md

@@ -33,102 +33,6 @@ A comprehensive [Model Context Protocol](https://modelcontextprotocol.io/introdu
 - **📖 Always Updated**: Documentation stays current with the latest HoloViz ecosystem changes.
 - **🔧 Zero Setup**: Works immediately with any MCP-compatible AI assistant.
 
-## 🚀 Quick Start
-
-### Requirements
-
-- Python 3.11+ and [uv](https://docs.astral.sh/uv/)
-- VS Code with GitHub Copilot, Claude Desktop, Cursor, or any other MCP-compatible client
-
-### Installation
-
-Install HoloViz MCP as a [uv tool](https://docs.astral.sh/uv/concepts/tools/):
-
-```bash
-uv tool install holoviz-mcp[panel-extensions]
-```
-
-Create the documentation index (takes up to 10 minutes on first run):
-
-```bash
-uvx holoviz-mcp update index
-```
-
-If you are using Github Copilot run
-
-```bash
-uvx holoviz-mcp update copilot
-```
-
-### Configure Your IDE
-
-**VS Code + GitHub Copilot**: Add this configuration to your `mcp.json`:
-
-```json
-{
-  "servers": {
-    "holoviz": {
-      "type": "stdio",
-      "command": "uvx",
-      "args": ["holoviz-mcp"]
-    }
-  },
-  "inputs": []
-}
-```
-
-**Claude Desktop**: Add to your configuration file (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):
-
-```json
-{
-  "mcpServers": {
-    "holoviz": {
-      "command": "uvx",
-      "args": ["holoviz-mcp"]
-    }
-  }
-}
-```
-
-**Cursor**: Go to `Cursor Settings` → `Features` → `Model Context Protocol` → `Add Server`:
-
-```json
-{
-  "name": "holoviz",
-  "command": "uvx",
-  "args": ["holoviz-mcp"]
-}
-```
-
-Restart your IDE and start asking about HoloViz documentation and Panel components!
-
-### Using Docker
-
-For containerized deployment:
-
-```bash
-# Pull the latest image
-docker pull ghcr.io/marcskovmadsen/holoviz-mcp:latest
-
-# Run with HTTP transport
-docker run -it --rm \
-  -p 8000:8000 \
-  -e HOLOVIZ_MCP_TRANSPORT=http \
-  -v ~/.holoviz-mcp:/root/.holoviz-mcp \
-  ghcr.io/marcskovmadsen/holoviz-mcp:latest
-```
-
-See the [Docker Guide](https://marcskovmadsen.github.io/holoviz-mcp/how-to/docker/) for more details.
-
-## 💡 Example Usage
-
-Ask your AI assistant questions like:
-
-- *"What Panel components are available for user input?"*
-- *"Show me how to create a dashboard with Panel Material UI components"*
-- *"What parameters does the Button component accept?"*
-- *"How do I deploy a Panel application?"*
-
 Watch the [HoloViz MCP Introduction](https://youtu.be/M-YUZWEeSDA) on YouTube to see it in action.
 
 [![HoloViz MCP Introduction](docs/assets/images/holoviz-mcp-introduction.png)](https://youtu.be/M-YUZWEeSDA)

docs/explanation/security.md

@@ -189,7 +189,7 @@ HoloViz MCP depends on:
 ### Update Command
 
 ```bash
-uv tool update holoviz-mcp[panel-extensions]
+uv tool update holoviz-mcp
 ```
 
 ## Logging & Monitoring

docs/how-to/installation.md

@@ -25,17 +25,14 @@ For other installation methods, see the [uv installation guide](https://docs.ast
 Install HoloViz MCP as a uv tool:
 
 ```bash
-uv tool install holoviz-mcp[panel-extensions]
+uv tool install holoviz-mcp
 ```
 
-This installs HoloViz MCP with Panel extensions like Material UI, Graphic Walker, and others.
+### Install Chromium
 
-!!! tip
-    If you want to be able to use the `panel_take_screenshot` tool, you will need to install [playwright](https://playwright.dev/python/) and chromium
-    ```bash
-    uv tool install holoviz-mcp[panel-extensions,playwright]
-    uvx --from holoviz-mcp playwright install chromium
-    ```
+```bash
+uvx holoviz-mcp install chromium
+```
 
 ### Create Documentation Index
 
@@ -62,7 +59,7 @@ Press `Ctrl+C` to stop the server.
 You can also install HoloViz MCP using pip:
 
 ```bash
-pip install holoviz-mcp[panel-extensions]
+pip install holoviz-mcp
 ```
 
 Then create the documentation index:
@@ -101,24 +98,6 @@ cd holoviz-mcp
 pip install -e .[dev]
 ```
 
-## Optional Dependencies
-
-### Panel Extensions
-
-Install with common Panel extensions:
-
-```bash
-uv tool install holoviz-mcp[panel-extensions]
-```
-
-This includes:
-- `panel-material-ui`: Material Design components
-- `panel-graphic-walker`: Interactive data visualization
-- `panel-full-calendar`: Calendar components
-- `panel-neuroglancer`: Neuroglancer integration
-- `panel-precision-slider`: High-precision sliders
-- `panel-web-llm`: WebLLM integration
-
 ### Development Dependencies
 
 For development work:
@@ -138,7 +117,7 @@ For containerized deployment, see the [Docker Guide](docker.md).
 ### Update with uv
 
 ```bash
-uv tool update holoviz-mcp[panel-extensions]
+uv tool update holoviz-mcp
 ```
 
 ### Update Documentation Index

docs/how-to/troubleshooting.md

@@ -62,7 +62,7 @@ Install a newer Python version if needed.
 4. Reinstall HoloViz MCP:
    ```bash
    uv tool uninstall holoviz-mcp
-   uv tool install holoviz-mcp[panel-extensions]
+   uv tool install holoviz-mcp
    ```
 
 ### Server Crashes

docs/how-to/updates.md

@@ -9,13 +9,13 @@ Keep HoloViz MCP up to date to ensure you have the latest features, bug fixes, a
 Update the HoloViz MCP package:
 
 ```bash
-uv tool update holoviz-mcp[panel-extensions]
+uv tool update holoviz-mcp
 ```
 
 ### With pip
 
 ```bash
-pip install --upgrade holoviz-mcp[panel-extensions]
+pip install --upgrade holoviz-mcp
 ```
 
 ### With conda/mamba
@@ -39,7 +39,7 @@ This ensures you have the latest documentation from HoloViz projects.
 For convenience, update both the package and documentation:
 
 ```bash
-uv tool update holoviz-mcp[panel-extensions] && uvx holoviz-mcp update index
+uv tool update holoviz-mcp && uvx holoviz-mcp update index
 ```
 
 ## Update Docker Image
@@ -119,7 +119,7 @@ Update when:
 If an update causes issues, rollback to a previous version:
 
 ```bash
-uv tool install holoviz-mcp[panel-extensions]==0.1.0
+uv tool install holoviz-mcp==0.1.0
 ```
 
 Replace `0.1.0` with the desired version.

docs/tutorials/getting-started.md

@@ -2,50 +2,55 @@
 
 This tutorial will guide you through installing and using HoloViz MCP for the first time. By the end, you'll have HoloViz MCP running and be able to ask your AI assistant questions about Panel components!
 
-## What You'll Learn
-
-- How to install HoloViz MCP
-- How to configure it with your AI assistant (VS Code, Claude Desktop, or Cursor)
-- How to use it to get help building Panel applications
-- How to verify everything is working correctly
-
-## Prerequisites
-
-Before you begin, ensure you have:
-
-- **Python 3.11 or newer** installed on your system
-- **[uv](https://docs.astral.sh/uv/)** package installer
-- An **MCP-compatible AI assistant**:
-    - VS Code with GitHub Copilot extension
-    - Claude Desktop application
-    - Cursor IDE
-    - Or any other MCP-compatible client
+!!! tip "What you'll learn"
+    - How to install HoloViz MCP
+    - How to configure it with your AI assistant (VS Code, Claude Desktop, or Cursor)
+    - How to use it to get help building Panel applications
+    - How to verify everything is working correctly
+
+!!! Prerequisites
+    Before you begin, ensure you have:
+
+    - **Python 3.11 or newer** installed on your system
+    - **[uv](https://docs.astral.sh/uv/)** package installer
+    - An **MCP-compatible AI assistant**:
+        - VS Code with GitHub Copilot extension
+        - Claude Desktop application
+        - Cursor IDE
+        - Or any other MCP-compatible client
 
 ## Step 1: Install HoloViz MCP
 
 Open your terminal and install HoloViz MCP as a uv tool:
 
 ```bash
-uv tool install holoviz-mcp[panel-extensions]
+uv tool install holoviz-mcp
 ```
 
-This command installs HoloViz MCP along with common Panel extensions, making them available for your AI assistant to reference.
+This command installs HoloViz MCP, making it available for your AI assistant to reference.
+
+!!! tip "What's happening?"
+    The uv tool manager creates an isolated environment for HoloViz MCP and installs all necessary dependencies.
 
-**What's happening?** The uv tool manager creates an isolated environment for HoloViz MCP and installs all necessary dependencies.
+## Step 2: Install Chromium
 
-## Step 2: Create the Documentation Index
+Install [Chromium](https://playwright.dev/docs/browsers) to enable the holoviz-mcp server to take screenshots:
+
+```bash
+uvx holoviz-mcp install chromium
+```
+
+## Step 3: Create the Documentation Index
 
 HoloViz MCP needs to index the HoloViz documentation to provide intelligent answers. Run:
 
 ```bash
 uvx holoviz-mcp update index
 ```
 
-**⏱️ This takes 5-10 minutes on first run** as it downloads and indexes documentation from Panel, hvPlot, and other HoloViz libraries.
-
-**Tip**: While this runs, continue to Step 3 to configure your IDE!
+**⏱️ This takes 5-10 minutes** as it downloads and indexes documentation from Panel, hvPlot, and other HoloViz libraries.
 
-## Step 3: Configure Your AI Assistant
+## Step 4: Configure Your AI Assistant
 
 Choose your AI assistant and follow the appropriate configuration:
 
@@ -54,7 +59,7 @@ Choose your AI assistant and follow the appropriate configuration:
 1. In VS Code, open the Command Palette (`Ctrl+Shift+P` or `Cmd+Shift+P`)
 2. Type "MCP: Add Server..." and press Enter
 3. Choose "Command (stdio)"
-4. Choose "uvx holoviz-mcp[panel-extensions]" as the "Command to run"
+4. Choose "uvx holoviz-mcp" as the "Command to run"
 5. Enter "holoviz" as the "Server ID"
 6. Choose "Global"
 
@@ -66,7 +71,7 @@ This will add the below configuration to you global `mcp.json` file.
     "holoviz": {
       "type": "stdio",
       "command": "uvx",
-      "args": ["holoviz-mcp[panel-extensions]"]
+      "args": ["holoviz-mcp"]
     }
   },
   "inputs": []
@@ -89,7 +94,7 @@ Please refer to the [VS Code | MCP Servers](https://code.visualstudio.com/docs/c
   "mcpServers": {
     "holoviz": {
       "command": "uvx",
-      "args": ["holoviz-mcp[panel-extensions]"]
+      "args": ["holoviz-mcp"]
     }
   }
 }
@@ -107,13 +112,13 @@ Please refer to the [VS Code | MCP Servers](https://code.visualstudio.com/docs/c
 {
   "name": "holoviz",
   "command": "uvx",
-  "args": ["holoviz-mcp[panel-extensions]"]
+  "args": ["holoviz-mcp"]
 }
 ```
 
 4. Save and restart Cursor
 
-## Step 4: Verify Installation
+## Step 5: Verify Installation
 
 Let's verify that HoloViz MCP is working correctly!
 
@@ -152,7 +157,7 @@ Open a chat with your AI assistant and try these questions:
 
 If your AI assistant provides detailed, accurate answers with specific Panel component information, congratulations! HoloViz MCP is working correctly! 🎉
 
-## Step 5: Build Your First Dashboard
+## Step 6: Build Your First Dashboard
 
 Now that everything is set up, let's build a simple dashboard:
 
@@ -215,6 +220,7 @@ In this tutorial, you:
 
 ✅ Installed HoloViz MCP using uv
 ✅ Created the documentation index
+✅ Installed Chromium
 ✅ Configured your AI assistant
 ✅ Verified the installation
 ✅ Built your first Panel dashboard

pyproject.toml

@@ -47,8 +47,14 @@ dependencies = [
     "matplotlib",
     "nbconvert",
     "packaging",
+    "panel-full-calendar",
+    "panel-graphic-walker",
     "panel-material-ui",
+    "panel-neuroglancer",
+    "panel-precision-slider",
+    "panel-web-llm",
     "panel",
+    "playwright",
     "plotly",
     "pydantic>=2.0",
     "PyYAML",
@@ -79,16 +85,6 @@ mypy = [
     "types-requests",
     "typing-extensions",
 ]
-panel-extensions =[
-    "panel-full-calendar",
-    "panel-graphic-walker",
-    "panel-neuroglancer",
-    "panel-precision-slider",
-    "panel-web-llm",
-]
-playwright = [
-    "playwright",
-]
 [tool.ruff]
 exclude = [
     ".git",