# Jupyter MCP Server (MCP server)

> Jupyter MCP Server is an MCP server that adds data and analytics tools to AI assistants such as Claude Desktop, Claude Code and Cursor. 🪐 🔧 Model Context Protocol (MCP) Server for Jupyter. It has 1,297 GitHub stars, is released under the BSD-3-Clause license and runs locally with uvx jupyter_mcp_server.

An MCP server developed for AI to connect and manage Jupyter Notebooks in real-time — and scale your Code Sandbox from local to the cloud (Datalayer, Kaggle, Google Colab, Modal, Daytona, E2B, CoreWeave, Cloudflare...)

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/datalayer/jupyter-mcp-server |
| GitHub stars | 1,297 |
| License | BSD-3-Clause |
| Language | Python |
| Transport | stdio |
| Packages | pypi: jupyter_mcp_server |
| Remote URL | none |
| Needs API key | yes |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Data & analytics |
| Latest release | v2.2.3 (Sep 26, 2026) |
| Last commit | Oct 5, 2026 |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "jupyter-mcp-server": {
      "command": "uvx",
      "args": [
        "jupyter_mcp_server"
      ],
      "env": {
        "JUPYTER_TOKEN": "your-value"
      }
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --env JUPYTER_TOKEN=your-value --transport stdio jupyter-mcp-server -- uvx jupyter_mcp_server
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "jupyter-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "jupyter_mcp_server"
      ],
      "env": {
        "JUPYTER_TOKEN": "your-value"
      }
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "inputs": [
    {
      "type": "promptString",
      "id": "jupyter_token",
      "description": "JUPYTER_TOKEN",
      "password": true
    }
  ],
  "servers": {
    "jupyter-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "jupyter_mcp_server"
      ],
      "env": {
        "JUPYTER_TOKEN": "${input:jupyter_token}"
      }
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Environment variables

- `JUPYTER_URL`: Shown in the README's example configuration.
- `JUPYTER_TOKEN` (secret): Shown in the README's example configuration.
- `ALLOW_IMG_OUTPUT`: Shown in the README's example configuration.

## Similar MCP servers

- [Ida Pro MCP](https://appsgit.com/mcp-servers/ida-pro-mcp): AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP. (12,497 stars, MIT)
- [Ask Jev](https://appsgit.com/mcp-servers/ask-jev): Evaluate state with typed choice, score, and probability questions. (5,174 stars, MIT, needs API key)
- [Jitsu](https://appsgit.com/mcp-servers/jitsu): Manage Jitsu data pipelines: destinations, streams, connections, functions, live events. (5,101 stars, MIT, official)
- [Google Ads + Meta Ads + SEO/GEO MCP](https://appsgit.com/mcp-servers/google-ads-meta-ads-seo-geo-mcp): Google Ads, Meta Ads, SEO, GEO & GA4 MCP by Ryze AI - audits, reports, keywords, Search Console. (4,107 stars, MIT)
- [Blitz](https://appsgit.com/mcp-servers/blitz): Give AI agents full control over iOS/macOS development via a native macOS app with 30+ MCP tools. (1,754 stars, Apache-2.0)
- [Chunkhound](https://appsgit.com/mcp-servers/chunkhound): Your entire engineering context, deeply understood. (1,445 stars, MIT, official)

---

Canonical page: https://appsgit.com/mcp-servers/jupyter-mcp-server
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.