Skip to main content
hc
Submit
mcpSource-backed
Jupyter MCP Server logo

Jupyter MCP Server

MCP server for connecting Claude to Jupyter notebooks, kernels, files, cells, multimodal outputs, and JupyterLab workflows over stdio or Streamable HTTP.

by Datalayer · submitted by oktofeesh1·added 2026-06-06·
Claude CodeClaude Desktop
HarnessClaude CodeClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/mcp/jupyter-mcp-server
Source URLs
https://raw.githubusercontent.com/datalayer/jupyter-mcp-server/main/README.md, https://github.com/datalayer/jupyter-mcp-server
Brand
Jupyter MCP Server
Brand domain
jupyter.org
Brand asset source
brandfetch
Safety notes
Jupyter MCP Server can list files, list kernels, create or switch notebooks, insert cells, edit cell source, delete cells, move cells, restart kernels, execute cells, and execute arbitrary code in a notebook kernel., Notebook code can read files available to the Jupyter process, access environment variables, call network services, start subprocesses, install packages, or mutate data depending on kernel permissions., File and notebook tools can alter important notebooks or delete work if pointed at the wrong server, path, notebook, or cell index., Keep Claude connected only to isolated kernels and directories that are appropriate for agent-driven execution., Use least-privilege Jupyter tokens, short-lived sessions, and a separate test notebook before allowing changes in production or shared JupyterHub environments., Streamable HTTP deployments require MCP client authentication unless explicitly started in insecure no-auth mode; do not expose no-auth transports beyond trusted local testing.
Privacy notes
Jupyter tokens, notebook contents, code cells, markdown cells, outputs, plots, image data, file names, kernel lists, environment-derived values, and error traces can be exposed to the MCP client., Executed notebook cells may print secrets, local paths, database results, API responses, or private research data into model context or client logs., Multimodal output support can send generated plots and images to the MCP client; disable or scope `ALLOW_IMG_OUTPUT` when images may contain sensitive data., Shared notebooks and JupyterHub deployments may contain other users' work; confirm workspace boundaries before connecting an agent., Retain notebook execution logs, MCP logs, and generated outputs only as long as needed for the workflow.
Author
Datalayer
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done

  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

20 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

5 to clear

Platforms

2 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done

  • Review privacy notesRequired

    Privacy notes are present.

    Done

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup. Have accounts and credentials ready first. Includes a review or approval gate.

0/5 ready
Account & credentials2Install & runtime2Review & approval120 minutes

Safety & privacy surface

Safety & privacy surface

6 safety and 5 privacy notes across 6 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.

6 areas
  • SafetyLocal filesJupyter MCP Server can list files, list kernels, create or switch notebooks, insert cells, edit cell source, delete cells, move cells, restart kernels, execute cells, and execute arbitrary code in a notebook kernel.
  • SafetyPermissions & scopesNotebook code can read files available to the Jupyter process, access environment variables, call network services, start subprocesses, install packages, or mutate data depending on kernel permissions.
  • SafetyLocal filesFile and notebook tools can alter important notebooks or delete work if pointed at the wrong server, path, notebook, or cell index.
  • SafetyGeneralKeep Claude connected only to isolated kernels and directories that are appropriate for agent-driven execution.
  • SafetyCredentials & tokensUse least-privilege Jupyter tokens, short-lived sessions, and a separate test notebook before allowing changes in production or shared JupyterHub environments.
  • SafetyNetwork accessStreamable HTTP deployments require MCP client authentication unless explicitly started in insecure no-auth mode; do not expose no-auth transports beyond trusted local testing.
  • PrivacyCredentials & tokensJupyter tokens, notebook contents, code cells, markdown cells, outputs, plots, image data, file names, kernel lists, environment-derived values, and error traces can be exposed to the MCP client.
  • PrivacyCredentials & tokensExecuted notebook cells may print secrets, local paths, database results, API responses, or private research data into model context or client logs.
  • PrivacyPermissions & scopesMultimodal output support can send generated plots and images to the MCP client; disable or scope `ALLOW_IMG_OUTPUT` when images may contain sensitive data.
  • PrivacyGeneralShared notebooks and JupyterHub deployments may contain other users' work; confirm workspace boundaries before connecting an agent.
  • PrivacyData retentionRetain notebook execution logs, MCP logs, and generated outputs only as long as needed for the workflow.

Disclosure: Datalayer-maintained open source MCP server for Jupyter, published as the `jupyter-mcp-server` Python package under the BSD 3-Clause license.

Safety notes

  • Jupyter MCP Server can list files, list kernels, create or switch notebooks, insert cells, edit cell source, delete cells, move cells, restart kernels, execute cells, and execute arbitrary code in a notebook kernel.
  • Notebook code can read files available to the Jupyter process, access environment variables, call network services, start subprocesses, install packages, or mutate data depending on kernel permissions.
  • File and notebook tools can alter important notebooks or delete work if pointed at the wrong server, path, notebook, or cell index.
  • Keep Claude connected only to isolated kernels and directories that are appropriate for agent-driven execution.
  • Use least-privilege Jupyter tokens, short-lived sessions, and a separate test notebook before allowing changes in production or shared JupyterHub environments.
  • Streamable HTTP deployments require MCP client authentication unless explicitly started in insecure no-auth mode; do not expose no-auth transports beyond trusted local testing.

Privacy notes

  • Jupyter tokens, notebook contents, code cells, markdown cells, outputs, plots, image data, file names, kernel lists, environment-derived values, and error traces can be exposed to the MCP client.
  • Executed notebook cells may print secrets, local paths, database results, API responses, or private research data into model context or client logs.
  • Multimodal output support can send generated plots and images to the MCP client; disable or scope `ALLOW_IMG_OUTPUT` when images may contain sensitive data.
  • Shared notebooks and JupyterHub deployments may contain other users' work; confirm workspace boundaries before connecting an agent.
  • Retain notebook execution logs, MCP logs, and generated outputs only as long as needed for the workflow.

Prerequisites

  • Python 3.10 or newer with `uvx` available.
  • A running JupyterLab, Jupyter Server, JupyterHub, or compatible notebook deployment.
  • A Jupyter access token for the notebook server Claude is allowed to control.
  • Review of notebook trust, kernel permissions, filesystem scope, and network access before enabling code-execution tools.
  • An `MCP_TOKEN` or equivalent bearer-token plan when using Streamable HTTP transport; avoid unauthenticated HTTP deployments.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
20 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
Datalayer-maintained open source MCP server for Jupyter, published as the `jupyter-mcp-server` Python package under the BSD 3-Clause license.
Full copyable content
{
  "mcpServers": {
    "jupyter": {
      "command": "uvx",
      "args": ["jupyter-mcp-server@latest"],
      "env": {
        "JUPYTER_URL": "YOUR_JUPYTER_SERVER_URL",
        "JUPYTER_TOKEN": "YOUR_JUPYTER_TOKEN",
        "ALLOW_IMG_OUTPUT": "true"
      }
    }
  }
}

About this resource

Content

Jupyter MCP Server connects Claude and other MCP clients to Jupyter notebooks. It exposes tools for browsing server files and kernels, selecting notebooks, reading notebook contents, editing cells, executing code, restarting kernels, and returning notebook outputs including images and plots.

Use it when Claude needs supervised access to a Jupyter environment for data science, research notebooks, reproducible experiments, interactive teaching, or notebook maintenance workflows.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, license, package manifest, architecture notes, CLI entrypoint, server implementation, runtime configuration, and tool registry for current setup and behavior details.

Features

  • Connect to local, remote, or hosted Jupyter notebook deployments.
  • List files and directories visible to the Jupyter server.
  • List available and running kernel sessions.
  • Create, select, switch, read, restart, and disconnect notebooks.
  • Read individual cells and full notebook contents.
  • Insert, delete, move, overwrite, and surgically edit cell source.
  • Execute individual cells or direct kernel code.
  • Return text, image, plot, and other notebook output types.
  • Use stdio for local MCP clients or Streamable HTTP for hosted clients.
  • Integrate with selected JupyterLab commands through jupyter-mcp-tools.

Installation

Start or identify the Jupyter server that Claude should control, then configure the MCP client with the published package:

{
  "mcpServers": {
    "jupyter": {
      "command": "uvx",
      "args": ["jupyter-mcp-server@latest"],
      "env": {
        "JUPYTER_URL": "YOUR_JUPYTER_SERVER_URL",
        "JUPYTER_TOKEN": "YOUR_JUPYTER_TOKEN",
        "ALLOW_IMG_OUTPUT": "true"
      }
    }
  }
}

Claude Code users can add it with:

claude mcp add jupyter --env JUPYTER_URL=YOUR_JUPYTER_SERVER_URL --env JUPYTER_TOKEN=YOUR_JUPYTER_TOKEN -- uvx jupyter-mcp-server@latest

For Streamable HTTP deployments, configure an MCP_TOKEN for bearer-token authentication unless the server is intentionally limited to trusted local testing.

Use Cases

  • Ask Claude to inspect a notebook and summarize its cells and outputs.
  • Insert or update code cells in a controlled analysis notebook.
  • Execute a cell and use the returned output to fix errors or refine analysis.
  • Generate, inspect, and iterate on plots from a data-science notebook.
  • Switch between notebooks in a shared Jupyter workspace.
  • Restart a kernel and rerun selected cells during troubleshooting.
  • Use Claude as a notebook assistant in teaching, research, or exploratory prototyping environments.

Safety and Privacy

Jupyter MCP Server gives Claude operational access to notebooks and kernels. Connect it to disposable notebooks first, review every code-execution request, and keep it away from notebooks that hold production credentials or sensitive research unless you have an explicit approval workflow.

Notebook outputs and error traces often contain private paths, secrets, data samples, or screenshots. Treat MCP transcripts and notebook logs as sensitive artifacts, especially when ALLOW_IMG_OUTPUT is enabled or when the connected Jupyter server belongs to a shared team or JupyterHub deployment.

#jupyter#notebooks#data-science#python#code-execution

Source citations

Add this badge to your README

Show that Jupyter MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/jupyter-mcp-server.svg)](https://heyclau.de/entry/mcp/jupyter-mcp-server)

How it compares

Jupyter MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field
Jupyter MCP Server logoJupyter MCP Server

MCP server for connecting Claude to Jupyter notebooks, kernels, files, cells, multimodal outputs, and JupyterLab workflows over stdio or Streamable HTTP.

Open dossier
Colab MCP logoColab MCP Server

Connect Claude to a Google Colab runtime. Colab MCP starts a local FastMCP server and websocket proxy, waits for an authorized Colab-origin browser connection, then exposes the session's notebook and runtime tools to your MCP client over stdio.

Open dossier
Data API Builder logoData API Builder MCP Tools

MCP support in Azure Data API Builder for exposing configured database entities as MCP tools, including entity discovery and DML operations over Azure databases and supported on-premises data stores.

Open dossier
data.gouv.fr logodata.gouv.fr MCP Server

Official data.gouv.fr MCP server for searching French national open datasets, exploring organizations and data services, inspecting resources, querying tabular data, and retrieving dataset metrics through Claude.

Open dossier
Next steps
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
Submitteroktofeesh1oktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandJupyter MCP Server logoJupyter MCP ServerColab MCP logoColab MCPData API Builder logoData API Builderdata.gouv.fr logodata.gouv.fr
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorDatalayerGoogle ColabAzuredata.gouv.fr
Added2026-06-062026-06-062026-06-062026-06-06
Platforms
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Harness
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓Jupyter MCP Server can list files, list kernels, create or switch notebooks, insert cells, edit cell source, delete cells, move cells, restart kernels, execute cells, and execute arbitrary code in a notebook kernel. Notebook code can read files available to the Jupyter process, access environment variables, call network services, start subprocesses, install packages, or mutate data depending on kernel permissions. File and notebook tools can alter important notebooks or delete work if pointed at the wrong server, path, notebook, or cell index. Keep Claude connected only to isolated kernels and directories that are appropriate for agent-driven execution. Use least-privilege Jupyter tokens, short-lived sessions, and a separate test notebook before allowing changes in production or shared JupyterHub environments. Streamable HTTP deployments require MCP client authentication unless explicitly started in insecure no-auth mode; do not expose no-auth transports beyond trusted local testing.✓Colab MCP runs a local websocket proxy and waits for a Google Colab browser session to connect before proxying session tools. The server creates a bearer-style proxy token and accepts a single authorized Colab-origin websocket connection at a time. A connected Colab runtime can execute code and interact with notebooks, outputs, files, variables, packages, and mounted resources depending on the session and tools exposed by Colab. Use disposable notebooks or reviewed development sessions before allowing Claude to run code or inspect outputs. Avoid connecting notebooks that have access to production data, cloud credentials, private datasets, paid accelerators, or long-running jobs unless the workflow has explicit approval.✓Data API Builder MCP tools can expose database entity metadata and perform DML operations depending on DAB configuration and permissions. Built-in tools include entity discovery and record read, create, update, delete, aggregate, and execute-style workflows in the MCP source tree. The upstream README still labels endpoint support as coming soon while source, samples, and testing docs expose MCP behavior; verify the exact release before production use. Use least-privilege roles, disable DML tools where not required, and require approval before write, delete, execute, or stored-procedure operations. Do not connect MCP clients to production databases without backups, audit logging, query limits, and rollback procedures.✓The hosted endpoint is documented as publicly available without access restrictions, so treat requests and returned public-data context as externally visible. Tools are read-only but can retrieve dataset metadata, resource URLs, rows from tabular resources, service OpenAPI specs, metrics, and organization details that may influence decisions. Public open data can be stale, incomplete, licensed with reuse conditions, or unsuitable for operational decisions without checking the dataset publisher and update cadence. Tabular queries can return rows from large resources; use small page sizes and pagination instead of asking an agent to pull entire datasets through chat. If self-hosting, review MCP_HOST, allowed hosts, allowed origins, Sentry, Matomo, and API-environment settings before exposing the server.
Privacy notes✓Jupyter tokens, notebook contents, code cells, markdown cells, outputs, plots, image data, file names, kernel lists, environment-derived values, and error traces can be exposed to the MCP client. Executed notebook cells may print secrets, local paths, database results, API responses, or private research data into model context or client logs. Multimodal output support can send generated plots and images to the MCP client; disable or scope `ALLOW_IMG_OUTPUT` when images may contain sensitive data. Shared notebooks and JupyterHub deployments may contain other users' work; confirm workspace boundaries before connecting an agent. Retain notebook execution logs, MCP logs, and generated outputs only as long as needed for the workflow.✓Notebook code, prompts, outputs, logs, variables, datasets, file paths, runtime metadata, package lists, browser session details, and generated websocket tokens can be visible to the MCP client and model provider. Colab notebooks may contain API keys, OAuth tokens, mounted Drive paths, secrets in environment variables, private model weights, customer data, or unpublished research. Local log files are created under a temporary Colab MCP log directory by default unless a log directory is specified. Review Google Colab, MCP client, model provider, and organization retention policies before sending notebook or runtime context to an assistant.✓Entity metadata can expose database names, table names, view names, stored procedure names, field names, key fields, relationships, permissions, and role design. Read and DML tool calls can expose or change customer records, internal data, regulated fields, identifiers, audit fields, and business workflow state. Connection strings, role headers, MCP URLs, logs, request bodies, result payloads, and MCP transcripts can contain sensitive operational or personal data. Redact database values, connection details, entity names, role names, and query results before sharing prompts, screenshots, logs, or generated notes.✓Search terms, dataset interests, resource IDs, user-agent headers, request URLs, tool names, and returned dataset rows may be visible to the hosted MCP service, MCP client, model provider, and logs. The server includes optional Matomo and Sentry instrumentation in source; hosted deployments may apply their own analytics and error-reporting policies. Public datasets can still contain personal data, geographic sensitivity, business identifiers, or regulated information; review source metadata and reuse terms before sharing results. Avoid placing private investigation notes, customer context, or unpublished analysis inside prompts when a generic dataset search is enough.
Prerequisites
  • Python 3.10 or newer with `uvx` available.
  • A running JupyterLab, Jupyter Server, JupyterHub, or compatible notebook deployment.
  • A Jupyter access token for the notebook server Claude is allowed to control.
  • Review of notebook trust, kernel permissions, filesystem scope, and network access before enabling code-execution tools.
  • uv or uvx available to run the server from the GitHub repository.
  • Local MCP client that supports `notifications/tools/list_changed`.
  • Google Colab account and browser session you are authorized to use.
  • Local machine access, because upstream documents that the MCP client must run locally.
  • Reviewed Azure Data API Builder configuration with the MCP runtime section enabled.
  • Supported Azure or on-premises database connection configured through DAB.
  • DAB entity permissions, role headers, DML tool flags, and per-entity MCP settings reviewed before exposing tools.
  • MCP client support for the transport used by the deployed DAB server.
  • MCP client that supports Streamable HTTP or a remote MCP bridge such as mcp-remote.
  • Agreement on whether hosted data.gouv.fr MCP requests may be sent to the public hosted endpoint.
  • Public-data review process for datasets that may contain personal, sensitive, stale, or jurisdiction-specific information.
  • Python 3.13 or newer only if self-hosting the repository instead of using the hosted endpoint.
Install
uvx jupyter-mcp-server@latest
uvx git+https://github.com/googlecolab/colab-mcp
Enable the DAB runtime MCP section, start Data API Builder with the reviewed configuration, and connect an MCP client to the configured MCP path.
claude mcp add --transport http datagouv https://mcp.data.gouv.fr/mcp
Config
Manual-only setup:
claude mcp add jupyter --env JUPYTER_URL=YOUR_JUPYTER_SERVER_URL --env JUPYTER_TOKEN=YOUR_JUPYTER_TOKEN -- uvx jupyter-mcp-server@latest
{
  "mcpServers": {
    "colab-mcp": {
      "command": "uvx",
      "args": ["git+https://github.com/googlecolab/colab-mcp"],
      "timeout": 30000
    }
  }
}
Manual-only setup:
"mcp": {
  "enabled": true,
  "path": "/mcp"
}
{
  "mcpServers": {
    "datagouv": {
      "url": "https://mcp.data.gouv.fr/mcp",
      "type": "http"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Source-backed guides for putting this to work.

Build Claude MCP Servers

Master MCP server development from scratch.

Added 8mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by JSONbored

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.