MCP Jupyter Complete
A server for Jupyter notebook manipulation with position-based operations and VS Code integration.
MCP Jupyter Complete
A comprehensive Model Context Protocol (MCP) server for Jupyter notebook manipulation with position-based operations and VS Code integration.
Features
🎯 Position-Based Operations
list_cells- List all cells with indices and type informationget_cell_source- Get source code of specific cells by indexedit_cell_source- Edit cell content by indexinsert_cell- Insert new cells at specific positionsdelete_cell- Delete cells by index with automatic reindexing
🚀 Enhanced Operations
move_cell- Move cells between positionsconvert_cell_type- Convert between code/markdown/raw cellsbulk_edit_cells- Perform multiple operations in a single call
🔧 VS Code Integration
trigger_vscode_reload- Force VS Code to reload notebook files- File watcher support for automatic reloading
- VS Code workspace and settings generation
- Extension recommendations for optimal Jupyter experience
Installation
-
Clone the repository:
git clone https://github.com/tofunori/mcp-jupyter-complete.git cd mcp-jupyter-complete -
Install dependencies:
npm install -
Make executable (optional):
npm link
Configuration
Add to your ~/.claude.json configuration:
{
"mcpServers": {
"jupyter-complete": {
"command": "node",
"args": ["/path/to/mcp-jupyter-complete/src/index.js"]
}
}
}
Or if installed globally via npm:
{
"mcpServers": {
"jupyter-complete": {
"command": "mcp-jupyter-complete"
}
}
}
Usage Examples
Basic Cell Operations
// List all cells
await mcp.call("list_cells", {
notebook_path: "/path/to/notebook.ipynb"
});
// Get cell content
await mcp.call("get_cell_source", {
notebook_path: "/path/to/notebook.ipynb",
cell_index: 0
});
// Edit a cell
await mcp.call("edit_cell_source", {
notebook_path: "/path/to/notebook.ipynb",
cell_index: 1,
new_source: "print('Hello World!')"
});
Advanced Operations
// Insert a new markdown cell
await mcp.call("insert_cell", {
notebook_path: "/path/to/notebook.ipynb",
position: 2,
cell_type: "markdown",
source: "# New Section\\n\\nThis is a new markdown cell."
});
// Move a cell
await mcp.call("move_cell", {
notebook_path: "/path/to/notebook.ipynb",
from_index: 3,
to_index: 1
});
// Bulk operations
await mcp.call("bulk_edit_cells", {
notebook_path: "/path/to/notebook.ipynb",
operations: [
{
type: "edit",
cell_index: 0,
new_source: "# Updated title"
},
{
type: "convert",
cell_index: 1,
new_type: "markdown"
}
]
});
VS Code Integration
// Trigger VS Code reload
await mcp.call("trigger_vscode_reload", {
notebook_path: "/path/to/notebook.ipynb"
});
VS Code Setup
For optimal VS Code integration:
-
Install recommended extensions:
- Python
- Jupyter
- Jupyter Keymap
- Jupyter Renderers
-
Configure auto-reload: Add to VS Code settings:
{ "files.watcherExclude": { "**/.ipynb_checkpoints/**": true }, "notebook.diffEditor.ignoreTrimWhitespace": false } -
Use with Claude Code: When using with Claude Code, notebook changes made via MCP will automatically trigger VS Code to prompt for reload.
API Reference
Core Functions
| Function | Parameters | Description |
|---|---|---|
list_cells | notebook_path | Lists all cells with indices |
get_cell_source | notebook_path, cell_index | Gets cell source code |
edit_cell_source | notebook_path, cell_index, new_source | Edits cell content |
insert_cell | notebook_path, position, cell_type?, source? | Inserts new cell |
delete_cell | notebook_path, cell_index | Deletes cell |
Enhanced Functions
| Function | Parameters | Description |
|---|---|---|
move_cell | notebook_path, from_index, to_index | Moves cell position |
convert_cell_type | notebook_path, cell_index, new_type | Converts cell type |
bulk_edit_cells | notebook_path, operations[] | Bulk operations |
VS Code Functions
| Function | Parameters | Description |
|---|---|---|
trigger_vscode_reload | notebook_path | Forces VS Code reload |
Cell Types
Supported cell types:
code- Python/executable code cellsmarkdown- Markdown text cellsraw- Raw text cells
Error Handling
The server provides detailed error messages for:
- Invalid cell indices
- File read/write permissions
- Malformed notebook JSON
- Invalid cell type conversions
Development
Testing
npm test
Linting
npm run lint
Development Mode
npm run dev
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details.
Changelog
v1.0.0
- Initial release
- Position-based cell operations
- VS Code integration
- Bulk operations support
- Comprehensive error handling
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
AST2LLM for Go
An AST-powered tool that enhances LLM context by automatically injecting relevant Go code structures into prompts.
MCP Manager
An interactive CLI tool for managing MCP server configurations in the current directory.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers, without authentication.
Airflow MCP Server
Control Apache Airflow via its API using JWT authentication.
Multichain MCP Server
A toolkit for building and deploying AI agents with blockchain capabilities, featuring a Model Context Protocol (MCP) server.
Generic API MCP Server
A generic server to interact with any REST API, allowing you to query data, create items, and call methods.
ui-ticket-mcp
Human-to-AI code review bridge. Review UI prototypes in the browser, then let AI agents fix the code automatically via MCP.
Figma
Access and interact with Figma files and prototypes directly from AI agents.
Clappia
A Python-based server for programmatically managing Clappia applications, forms, and submissions via its API.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)