@ChengJiale150
基本情報
An MCP service specifically developed for AI to connect and manage Jupyter Notebooks
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"Jupyter-MCP-Server": {
"command": "uvx",
"args": [
"better-jupyter-mcp-server"
],
"env": {},
"transport": "stdio"
}
}
}Connect to a notebook and corresponding kernel. It is the FIRST STEP before ANY subsequent operations.
List all currently connected Notebooks. It will return unique name, Jupyter URL and Path of all connected Notebooks
Restart the kernel of a specified Notebook, clear all imported packages and variables
Read the source content (without output) of a connected Notebook. It will return the formatted content of the Notebook (including Index, Cell Type, Execution Count and Full Source Content). ONLY used when the user explicitly instructs to read the full content of the Notebook.
List the basic information of cells. It will return Index, Type, Execution Count and First Line of the Cell. It will be used to quickly overview the structure and current status of the Notebook or locate the index of specific cells for following operations(e.g. delete, insert).
Read the detailed content of a specific cell. It will return the source code, execution count and output of the cell.
Delete a specific cell. When deleting many cells, MUST delete them in descending order of their index.
Insert a cell at the specified index. Using `append_execute_cell` as a alternative if you want to insert at the end of the notebook and then execute it. When inserting many cells, MUST insert them in ascending order of their index.
Execute a specific cell with a timeout. It will return the output of the cell.
Overwrite the content of a specific cell It will return a comparison (diff style, `+` for new lines, `-` for deleted lines) of the cell's content.
Add a new cell to the end of a Notebook and immediately execute it. It will return the output of the cell. It is highly recommended for replacing the combination of `insert_cell` and `execute_cell` at the end of the Notebook.
Execute a temporary code block (not saved to the Notebook) and will return the output. It will recommend to use in following cases: 1. Execute Jupyter magic commands 2. Debug code 3. View intermediate variable values(e.g., `print(xxx)` or `df.head()`) 4. Perform temporary statistical calculations(e.g., `np.mean(df['xxx'])`) DO NOT USE IN THE FOLLOWING CASES: 1. Import new modules and perform variable assignments that affect subsequent Notebook execution 2. Run code that requires a long time to run
Jupyter MCP Server is a service based on the Model Context Protocol (MCP) that gives AI tools in advanced IDEs and CLI tools the ability to connect and manage Jupyter Notebooks for tasks like data analysis, visualization, and machine learning. It supports multiple Notebooks simultaneously, interactive execution, and multimodal output (text, images, tables).
Install via uvx with uvx better-jupyter-mcp-server or clone the source and run uv run fastmcp run src/better_jupyter_mcp_server/server.py. You must have a running Jupyter Server (e.g., jupyter lab --port 8888 --IdentityProvider.token YOUR_TOKEN) and provide the server URL and token in your client’s rules file. Then configure the MCP JSON with "command": "uvx" and "args": ["better-jupyter-mcp-server"] using stdio transport.
Unlike tools that only read/edit or handle a single Notebook, it manages multiple Notebooks interactively, supports multimodal output, and provides advanced integrated cells like `append_execute_cell` to reduce tool calls.
Python 3.12+, uv for installation, and a running Jupyter Server (Lab or Notebook) with a token. The server uses stdio transport and runs locally.
You provide the Jupyter server URL and token in your client’s rules file. The server then uses that token to authenticate all calls.
The `connect_notebook` tool can take 10–30 seconds because it starts a Kernel. Other tools execute quickly. Multimodal output requires a client that supports returning image data via MCP.
Notebooks and kernels run on the configured Jupyter Server (default localhost:8888). All data stays on that server; the MCP server does not store data externally.
Facebook & Instagram data for AI agents — pages, posts, groups, Ads Library, Marketplace, profiles and reels. 47 read-only tools with structured output.
Find the TikTok, YouTube and Instagram creators and the blogs, review sites and roundups already promoting your competitors, with the proof, then recruit them. 32 tools: competitor rosters, graded creators, roundup place
Real-time crypto whale tracking & market intelligence. Monitors 80+ verified whale wallets across 14 blockchains (BTC, ETH, SOL, BSC, Base, ARB, MATIC, TON, SUI, HYPE, TRX, SEI, INJ, APT). 55 tools: whale movements, fear
Cookieless web analytics your coding agent reads and remembers. Traffic, referrers and funnels over MCP, plus deploy-tagged before/after comparisons, stored site context, and proactive anomaly surfacing. Remote server, n
HasData's hosted Zillow MCP server lets AI agents search homes for sale, rentals and sold listings, then retrieve property details, price history and Zillow estimates as structured JSON.
コメント