Add the tools returned by jupyter_mcp_tools (#109)

* deps: jupyter-mcp-tools 0.1.1

* chore: depend on jupyter-mcp-tools 0.1.2

* docs: links

* jupyterlab mode + automatic notebook opening

* fix get_tools

* correct setup automated release notes

---------

Co-authored-by: Eléonore Charles <[email protected]>

Author: echarles

.github/workflows/release.yml

@@ -116,21 +116,20 @@ jobs:
         id: version
         run: echo "VERSION=${GITHUB_REF#refs/tags/v}" >> $GITHUB_OUTPUT
 
+      - name: Create Release with Auto-Generated Notes
+        run: |
+          gh release create ${{ github.ref_name }} \
+            --title "Release ${{ steps.version.outputs.VERSION }}" \
+            --generate-notes \
+            --notes "## 🚀 Release ${{ steps.version.outputs.VERSION }}
+
+          ### 🔗 Links
+
+          - [PyPI](https://pypi.org/project/jupyter-mcp-server/${{ steps.version.outputs.VERSION }}/)
+          - [Docker Hub](https://hub.docker.com/r/datalayer/jupyter-mcp-server)
 
-      - name: Create Release
-        uses: actions/create-release@v1
+          ---
+
+          ### What's Changed"
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          tag_name: ${{ github.ref }}
-          release_name: Release ${{ steps.version.outputs.VERSION }}
-          body: |
-            ## 🚀 Release ${{ steps.version.outputs.VERSION }}
-
-            ### 🔗 Links
-
-            - [PyPI](https://pypi.org/project/jupyter-mcp-server/${{ steps.version.outputs.VERSION }}/)
-            - [Docker Hub](https://hub.docker.com/r/datalayer/jupyter-mcp-server)
-          draft: false
-          prerelease: false
-          generate_release_notes: true

README.md

@@ -28,7 +28,7 @@
 <a href="https://archestra.ai/mcp-catalog/datalayer__jupyter-mcp-server"><img src="https://archestra.ai/mcp-catalog/api/badge/quality/datalayer/jupyter-mcp-server" alt="Trust Score" width="150"></a>
 
 
-> 🚨 **Latest Release: v0.14.0**: **Multi-notebook support!** You can now seamlessly switch between multiple notebooks in a single session. [📋 Read more in the release notes](https://jupyter-mcp-server.datalayer.tech/releases)
+> 🚨 **Latest Release: v17.0**: **JupyterLab Mode Integration!** Enhanced UI integration with automatic notebook opening. [📋 Read more in the release notes](https://jupyter-mcp-server.datalayer.tech/releases)
 
 ![Jupyter MCP Server Demo](https://assets.datalayer.tech/jupyter-mcp/mcp-demo-multimodal.gif)
 
@@ -42,14 +42,14 @@
 - [Contributing](#-contributing)
 - [Resources](#-resources)
 
-
 ## 🚀 Key Features
 
 - ⚡ **Real-time control:** Instantly view notebook changes as they happen.
 - 🔁 **Smart execution:** Automatically adjusts when a cell run fails thanks to cell output feedback.
 - 🧠 **Context-aware:** Understands the entire notebook context for more relevant interactions.
 - 📊 **Multimodal support:** Support different output types, including images, plots, and text.
 - 📚 **Multi-notebook support:** Seamlessly switch between multiple notebooks.
+- 🎨 **JupyterLab integration:** Enhanced UI integration like automatic notebook opening.
 - 🤝 **MCP-compatible:** Works with any MCP client, such as Claude Desktop, Cursor, Windsurf, and more.
 
 Compatible with any Jupyter deployment (local, JupyterHub, ...) and with [Datalayer](https://datalayer.ai/) hosted Notebooks.
@@ -89,6 +89,14 @@ The server provides a rich set of tools for interacting with Jupyter notebooks,
 | `insert_execute_code_cell` | A convenient tool to insert a new code cell and execute it in one step. |
 | `execute_ipython` | Execute IPython code directly in the kernel, including magic and shell commands. |
 
+### JupyterLab Integration
+
+*Available only when JupyterLab mode is enabled. It is enabled by default.*
+
+| Name | Description |
+|:---|:---|
+| `notebook_run-all-cells` | Execute all cells in the current notebook sequentially using JupyterLab's native commands. |
+
 For more details on each tool, their parameters, and return values, please refer to the [official Tools documentation](https://jupyter-mcp-server.datalayer.tech/tools).
 
 ## 🏁 Getting Started
@@ -98,7 +106,7 @@ For comprehensive setup instructions—including `Streamable HTTP` transport, ru
 ### 1. Set Up Your Environment
 
 ```bash
-pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 ipykernel
+pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 jupyter-mcp-tools>=0.1.4 ipykernel
 pip uninstall -y pycrdt datalayer_pycrdt
 pip install datalayer_pycrdt==0.12.17
 ```

docs/docs/configure/index.mdx

@@ -17,6 +17,9 @@ Options:
                                   Defaults to 'stdio'.
   --provider [jupyter|datalayer]  The provider to use for the document and
                                   runtime. Defaults to 'jupyter'.
+  --jupyterlab BOOLEAN           Enable JupyterLab mode for enhanced UI
+                                  integration like automatic notebook opening.
+                                  Defaults to True.
   --runtime-url TEXT              The runtime URL to use. For the jupyter
                                   provider, this is the Jupyter server URL.
                                   For the datalayer provider, this is the

docs/docs/deployment/jupyter/index.mdx

@@ -6,6 +6,12 @@ The Jupyter MCP Server acts as a bridge between the MCP client and the JupyterLa
 
 You can customize the setup further based on your requirements. Refer to the [server configuration](/configure) for more details on the possible configurations.
 
+:::tip JupyterLab Mode
+
+**New in v0.17.0**: Enable JupyterLab mode for enhanced UI integration! When enabled, notebooks automatically open in JupyterLab and additional UI tools become available. See the [JupyterLab Mode configuration](/configure#jupyterlab-mode) for details.
+
+:::
+
 Jupyter MCP Server supports two types of transport to connect to your MCP client: **STDIO** and **Streamable HTTP**. Choose the one that best fits your needs.
 For more details on the different transports, refer to the official MCP documentation [here](https://modelcontextprotocol.io/specification/2025-06-18/basic/transports).
 

docs/docs/deployment/jupyter/stdio/index.mdx

@@ -7,7 +7,7 @@
 Make sure you have the following packages installed in your environment. The collaboration package is needed as the modifications made on the notebook can be seen thanks to [Jupyter Real Time Collaboration](https://jupyterlab.readthedocs.io/en/stable/user/rtc.html).
 
 ```bash
-pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 ipykernel
+pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 jupyter-mcp-tools>=0.1.4 ipykernel
 pip uninstall -y pycrdt datalayer_pycrdt
 pip install datalayer_pycrdt==0.12.17
 ```

docs/docs/deployment/jupyter/streamable-http/jupyter-extension/index.mdx

@@ -9,7 +9,7 @@ Make sure you have the following packages installed in your environment. The col
 ```bash
 pip install "jupyter-mcp-server>=0.15.0" "jupyterlab==4.4.1" "jupyter-collaboration==4.0.2" "ipykernel"
 pip uninstall -y pycrdt datalayer_pycrdt
-pip install datalayer_pycrdt==0.12.17
+pip install datalayer_pycrdt==0.12.17 jupyter_mcp_tools
 ```
 
 ### JupyterLab and MCP start

docs/docs/deployment/jupyter/streamable-http/standalone/index.mdx

@@ -7,7 +7,7 @@
 Make sure you have the following packages installed in your environment. The collaboration package is needed as the modifications made on the notebook can be seen thanks to [Jupyter Real Time Collaboration](https://jupyterlab.readthedocs.io/en/stable/user/rtc.html).
 
 ```bash
-pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 ipykernel
+pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 jupyter-mcp-tools>=0.1.4 ipykernel
 pip uninstall -y pycrdt datalayer_pycrdt
 pip install datalayer_pycrdt==0.12.17
 ```

docs/docs/index.mdx

@@ -26,6 +26,7 @@ Key features include:
 - 🧠 **Context-aware:** Understands the entire notebook context for more relevant interactions.
 - 📊 **Multimodal support:** Support different output types, including images, plots, and text.
 - 📁 **Multi-notebook support:** Seamlessly switch between multiple notebooks.
+- 🎛️ **JupyterLab integration:** Enhanced UI integration like automatic notebook opening.
 - 🤝 **MCP-compatible:** Works with any MCP client, such as [Claude Desktop](/clients/claude_desktop), [Cursor](/clients/cursor), [Cline](/clients/cline), [Windsurf](/clients/windsurf) and more.
 
 To use Jupyter MCP Server, you first need to decide which setup fits your needs:

docs/docs/releases/index.mdx

@@ -1,6 +1,12 @@
 # Releases
 
-## 0.16.x - 13 Oct 2025
+## Latest Release
+
+See the latest release notes on the [GitHub Releases page](https://github.com/datalayer/jupyter-mcp-server/releases).
+
+## Older Releases
+
+### 0.16.x - 13 Oct 2025
 
 - [Merge the three execute tools into a single unified tool](https://github.com/datalayer/jupyter-mcp-server/pull/111)
 - [Docs: update readme and contributing](https://github.com/datalayer/jupyter-mcp-server/pull/112)
@@ -10,45 +16,45 @@
 - [Refactor: separate and simplify the server.py](https://github.com/datalayer/jupyter-mcp-server/pull/123)
 - [Feat/add JUPYTER_URL and JUPYTER_TOKEN](https://github.com/datalayer/jupyter-mcp-server/pull/125)
 
-## 0.15.x - 08 Oct 2025
+### 0.15.x - 08 Oct 2025
 
 - [Run as Jupyter Server Extension + Tool registry + Use tool](https://github.com/datalayer/jupyter-mcp-server/pull/95)
 - [simplify tool implementations](https://github.com/datalayer/jupyter-mcp-server/pull/101)
 - [add uvx as alternative MCP server startup method](https://github.com/datalayer/jupyter-mcp-server/pull/101)
 - [document as a Jupyter Extension](https://github.com/datalayer/jupyter-mcp-server/pull/101)
 - Fix Minor Bugs: [#108](https://github.com/datalayer/jupyter-mcp-server/pull/108),[#110](https://github.com/datalayer/jupyter-mcp-server/pull/110)
 
-## 0.14.0 - 03 Oct 2025
+### 0.14.0 - 03 Oct 2025
 
 - [Additional Tools & Bug fixes](https://github.com/datalayer/jupyter-mcp-server/pull/93).
 - [Execute IPython](https://github.com/datalayer/jupyter-mcp-server/pull/90).
 - [Multi notebook management](https://github.com/datalayer/jupyter-mcp-server/pull/88).
 
-## 0.13.0 - 25 Sep 2025
+### 0.13.0 - 25 Sep 2025
 
 - [Add multimodal output support for Jupyter cell execution](https://github.com/datalayer/jupyter-mcp-server/pull/75).
 - [Unify cell insertion functionality](https://github.com/datalayer/jupyter-mcp-server/pull/73).
 
-## 0.11.0 - 01 Aug 2025
+### 0.11.0 - 01 Aug 2025
 
 - [Rename room to document](https://github.com/datalayer/jupyter-mcp-server/pull/35).
 
-## 0.10.2 - 17 Jul 2025
+### 0.10.2 - 17 Jul 2025
 
 - [Tools docstring improvements](https://github.com/datalayer/jupyter-mcp-server/pull/30).
 
-## 0.10.1 - 11 Jul 2025
+### 0.10.1 - 11 Jul 2025
 
 - [CORS Support](https://github.com/datalayer/jupyter-mcp-server/pull/29).
 
-## 0.10.0 - 07 Jul 2025
+### 0.10.0 - 07 Jul 2025
 
 - More [fixes](https://github.com/datalayer/jupyter-mcp-server/pull/28) issues for nbclient stop.
 
-## 0.9.0 - 02 Jul 2025
+### 0.9.0 - 02 Jul 2025
 
 - Fix issues with `nbmodel` stops.
 
-## 0.6.0 - 01 Jul 2025
+### 0.6.0 - 01 Jul 2025
 
 - Configuration change, see details on the [clients page](/clients) and [server configuration](/configure).

docs/docs/tools/index.mdx

@@ -1,6 +1,6 @@
 # Tools
 
-The server currently offers 16 tools organized into 3 categories:
+The server currently offers 16 tools organized into 3 categories, plus 1 additional JupyterLab-specific tool:
 
 ## Server Management Tools (3 tools)
 
@@ -164,3 +164,16 @@ The server currently offers 16 tools organized into 3 categories:
   - `timeout`(int): Execution timeout in seconds (default: 60s)
 - Returns:
   - `list[Union[str, ImageContent]]`: List of outputs from the executed code (supports multimodal output including images)
+
+## JupyterLab-Specific Tools (1 tool)
+
+*Available only when JupyterLab mode is enabled (`--jupyterlab` or `jupyterlab: true` in config). It is set to `True` by default.*
+
+#### 17. `notebook_run-all-cells`
+
+- Execute all cells in the current notebook sequentially.
+- This tool provides a convenient way to run the entire notebook from start to finish, which is particularly useful for batch execution or notebook validation.
+- Only available when JupyterLab mode is enabled for enhanced UI integration.
+- Input: None
+- Returns: Success message indicating that all cells have been executed
+- Note: This tool uses JupyterLab's native execution commands for optimal performance and UI feedback.