AgentArmorHQ
Sign in

jupyter-mcp-server

MCP server · GitHub · ★ 1.3k · graded 2026-10-22Source linked

🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.

No outside reports on file

This tool gives AI direct code execution on your machine, so only use it with environments containing no sensitive data and keep Claude's access as limited as possible.

Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Jupyter MCP Server helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsRequires API key or tokenREVIEW
  • Package sourceGitHub (datalayer/jupyter-mcp-server)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/datalayer/jupyter-mcp-server ↗

All setup options ↓

Check this skillWatch it in my stackCompareREADME badgeView project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-22.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Jupyter MCP Server

This is a Model Context Protocol (MCP) server that connects Claude and other AI assistants to Jupyter notebooks and Python environments. It lets AI assistants run code, access notebook files, and interact with Jupyter kernels through a standardized protocol.

Who it’s for

Developers and data scientists who want Claude or similar AI tools to execute Python code and work with Jupyter notebooks directly. Teams building AI applications that need programmatic access to computational environments.

Alternatives

  • jupyter-kernel-gateway: Official Jupyter tool for exposing kernels as HTTP services (more standard but less AI-focused)
  • nbconvert with API wrappers: Convert notebooks to APIs manually with more control over what's exposed
  • Local Python REPL MCP servers: Generic Python execution servers without Jupyter coupling

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README. The installation process varies depending on your Jupyter setup and whether you're running it locally or in a container. Check https://github.com/datalayer/jupyter-mcp-server (opens external site) for specific installation steps for your environment.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

34/100
GitHub stars
1.3k
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • Code execution: The AI can run arbitrary Python code on your system with your user's permissions, potentially accessing or modifying any file your account can reach.
  • Data exposure: Jupyter notebooks may contain sensitive data (API keys, credentials, private datasets) that the AI could accidentally leak or expose in responses.
  • Kernel state: Code run through this connector shares your Jupyter kernel's memory and variables—the AI could access previously defined secrets or business logic.
  • Prompt injection: Malicious notebook content or code output could trick the AI into running unintended commands or bypassing safety guidelines.
  • No built-in sandboxing: Unlike some tools, this directly exposes kernel access without isolation layers, so compromised kernels mean compromised AI interactions.

How to lower the risk

Least-privilege permissions

  • Run Jupyter in a dedicated user account with minimal file system access
  • Don't store credentials or secrets in notebooks; use environment variables or secure vaults

Network isolation

  • Keep Jupyter listening only on localhost, not exposed to networks
  • Use firewall rules to block external access to the Jupyter port

Monitoring

  • Log all code executed through the MCP connector
  • Review Claude's responses for unexpected system commands or file access

Red flags to watch for

  • Claude asking to install packages or modify system settings
  • Requests to access files outside your project directory
  • Sudden changes in code behavior or unexpected error messages

Questions

How do I install Jupyter MCP Server?

Jupyter MCP Server does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/datalayer/jupyter-mcp-server.

Are there security reports about Jupyter MCP Server?

No reports found for this package in our research (last checked 2026-10-30). Jupyter MCP Server currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include code execution, data exposure, kernel state.

Is Jupyter MCP Server actively maintained?

Jupyter MCP Server has 1.3k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/datalayer/jupyter-mcp-server before pinning it in production.

What are alternatives to Jupyter MCP Server?

Notable alternatives to Jupyter MCP Server include jupyter-kernel-gateway (Official Jupyter tool for exposing kernels as HTTP services (more standard but less AI-focused)), nbconvert with API wrappers (Convert notebooks to APIs manually with more control over what's exposed), Local Python REPL MCP servers (Generic Python execution servers without Jupyter coupling). You can also compare Jupyter MCP Server side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

Maintain or use Jupyter MCP Server? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Jupyter MCP Server

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Jupyter MCP Server](https://agentarmorhq.com/api/badge/datalayer-jupyter-mcp-server)](https://agentarmorhq.com/skills/datalayer-jupyter-mcp-server)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/datalayer-jupyter-mcp-server"><img src="https://agentarmorhq.com/api/badge/datalayer-jupyter-mcp-server" alt="AgentArmorHQ Risk Grade for Jupyter MCP Server" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "datalayer-jupyter-mcp-server"

Share with your security lead

Need sign-off to use jupyter-mcp-server? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: jupyter-mcp-server
- **Listing URL:** https://agentarmorhq.com/skills/datalayer-jupyter-mcp-server
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.3k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (datalayer/jupyter-mcp-server)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/datalayer/jupyter-mcp-server
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
datalayer
Source code
github.com/datalayer/jupyter-mcp-server
Est. context load
~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
Popularity
1.3k GitHub stars
Last updated
2026-10-29
Last graded
2026-10-22

Community

Discussions for Jupyter MCP Server

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Jupyter MCP Server helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude