yarn that is installed with JupyterLab. You may use yarn or npm in lieu of jlpm below.

```bash

Clone the repo to your local environment

Change directory to the mcp_client_jupyter_chat directory

Install package in development mode

pip install -e "."

Link your development version of the extension with JupyterLab

jupyter labextension develop . --overwrite

Rebuild extension Typescript source after making changes

jlpm build ```

You can watch the source directory and run JupyterLab at the same time in different terminals to watch for changes in the extension's source and automatically rebuild the extension.

```bash

Watch the source directory in one terminal, automatically rebuilding when needed

jlpm watch

Run JupyterLab in another terminal

jupyter lab ```

With the watch command running, every saved change will immediately be built locally and available in your running JupyterLab. Refresh JupyterLab to load the change in your browser (you may need to wait several seconds for the extension to be rebuilt).

By default, the jlpm build command generates the source maps for this extension to make it easier to debug using the browser dev tools. To also generate source maps for the JupyterLab core extensions, you can run the following command:

bash jupyter lab build --minimize=False

Development uninstall

bash pip uninstall mcp_client_jupyter_chat

In development mode, you will also need to remove the symlink created by jupyter labextension develop command. To find its location, you can run jupyter labextension list to figure out where the labextensions folder is located. Then you can remove the symlink named mcp-client-jupyter-chat within that folder.

Testing the extension

Frontend tests

This extension is using Jest for JavaScript code testing.

To execute them, execute:

sh jlpm jlpm test

Integration tests

This extension uses Playwright for the integration tests (aka user level tests). More precisely, the JupyterLab helper Galata is used to handle testing the extension in JupyterLab.

More information are provided within the ui-tests README.

Packaging the extension

See RELEASE

20:T9cb,

MCP Client Notebook Test Prompts

This document contains sample prompts to test the MCP client notebook's ability to work with multiple tools and servers.

Setup

Before running these test prompts, make sure: 1. The notebook is running 2. Both the filesystem and memory servers are started 3. There is a filesystem-testing directory with some test files

Test Prompts

1. Multi-Tool Basic Test

What files are in the filesystem-testing directory and what's in memory? This tests the ability to: - Use the filesystem tool to list directory contents - Use the memory tool to show current memory state - Combine results from multiple tools

2. File Reading and Memory Test

Read the contents of hello.txt and store it in memory with the key 'hello_content' This tests the ability to: - Read a file from filesystem - Store data in memory - Chain multiple tool operations

3. Memory Operations Test

Store the text "This is a test" in memory with key "test_key" and then show what's in memory This tests the ability to: - Store data in memory - Retrieve memory contents - Perform sequential operations

4. File System Navigation Test

What directories are allowed in the filesystem server? This tests the

Discover MCP Clients

Find the best MCP clients for your needs.

MCP CLI client

mcp-client-jupyter-chat

mcp-client-notebook

airtable-mcp

codename goose

mcp-sse-proxy

fast-mcp-client

MCP-on-FHIR