vscode-notebook-mcp
Exposes VSCode Jupyter notebooks to MCP-compatible AI agents, enabling them to read, edit, and run cells against the same kernel.
README
vscode-notebook-mcp
A VS Code extension that exposes the Jupyter notebooks in your VSCode editor to MCP-compatible AI agents (e.g. Claude Code). The agent reads, edits, and runs cells against the same kernel VS Code is using.
Status: pre-alpha, single-developer project. Built fresh; not a fork.
Tools (13)
Discovery
| Tool | Description |
|---|---|
notebook_list_open |
List all open notebooks with URI, file name, cell count, and which is active |
notebook_open |
Open a .ipynb file (absolute path, file:// URI, or workspace-relative) so its cells become available |
notebook_list_cells |
List cells with index, kind, language, preview, execution state |
notebook_get_cell_content |
Full source of a cell |
notebook_get_cell_output |
Outputs of a cell (text, errors, images as base64) |
Cell manipulation
| Tool | Description |
|---|---|
notebook_insert_cell |
Insert a code or markdown cell at any position; optionally execute |
notebook_edit_cell |
Replace contents of an existing cell |
notebook_delete_cell |
Delete a cell by index |
Execution
| Tool | Description |
|---|---|
notebook_run_cell |
Execute an existing code cell and return outputs |
notebook_clear_cell_output |
Clear outputs of one cell |
notebook_clear_all_outputs |
Clear outputs of every cell |
Kernel
| Tool | Description |
|---|---|
notebook_get_kernel_info |
Language, status, notebook URI |
notebook_select_kernel |
Programmatic by kernel_id, or open the kernel picker if omitted |
All tools accept an optional notebook_uri (omitted → uses the active notebook editor) and response_format ("markdown" or "json").
Setup
- Install the Jupyter extension in VS Code if you don't already have it.
- Build and run this extension:
Then open this folder in VS Code and press F5 to launch an Extension Development Host with the extension loaded.npm install npm run build - Add to your MCP client config:
{ "mcpServers": { "notebook": { "url": "http://127.0.0.1:49777/mcp" } } } - Open a
.ipynbfile in the Extension Development Host. Look for the🪐 :49777indicator in the status bar.
Configuration
| Setting | Default | Description |
|---|---|---|
notebook-mcp.port |
49777 |
Preferred port. Auto-increments if busy (up to +99). |
Commands
Notebook MCP: Restart ServerNotebook MCP: Show Server Info
Architecture
┌─────────────────────────────────────────────────────────┐
│ VS Code window │
│ │
│ ┌───────────────────────────────────────────────────┐ │
│ │ Jupyter extension (ms-toolsai.jupyter) │ │
│ │ │ │
│ │ Notebook document ◄──► Kernel ──► Outputs │ │
│ └───────────────────────────────────────────────────┘ │
│ ▲ │
│ │ vscode.NotebookEdit, │
│ │ notebook.cell.execute, │
│ │ jupyter.kernels.getKernel │
│ │ │
│ ┌───────────────────────┴───────────────────────────┐ │
│ │ This extension │ │
│ │ │ │
│ │ HTTP server :49777 ──► MCP tools (12) │ │
│ │ (StreamableHTTPServerTransport) │ │
│ └───────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────┘
│ HTTP (MCP protocol)
▼
┌───────────────────────────────┐
│ AI agent │
│ (Claude Code, Cursor, etc.) │
└───────────────────────────────┘
Implementation notes
- Writes go through
vscode.NotebookEdit+vscode.WorkspaceEdit, preserving undo/redo. - Execution dispatches
notebook.cell.executeand waits by pollingcell.executionSummary.successfor abooleanvalue (VS Code creates the summary as soon as execution starts butsuccessonly becomes a boolean when the kernel finishes). - Inserted cells are tagged with a metadata id so the executor can find them again after the index shifts due to other concurrent edits.
- Multi-notebook: every tool accepts
notebook_uri. Resolution: explicit URI → look up invscode.workspace.notebookDocuments(or open it); otherwise fall back tovscode.window.activeNotebookEditor.
Development
npm install
npm run build # esbuild bundle
npm run watch # rebuild on change
npm run typecheck # tsc --noEmit
npm test # vitest (no tests yet)
Press F5 in VS Code to launch the Extension Development Host.
References
Other projects along similar lines to this project:
- datalayer/jupyter-mcp-server — MCP server that talks to a running Jupyter server via HTTP/WebSocket.
- olavocarvalho/vscode-runtime-notebook-mcp — similar architecture as this project (VS Code Notebook API + embedded HTTP MCP server).
I built this fresh to learn and so I have room to tweak the design and develop new features.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。