jupyter-mcp-server MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Real-time control of a running Jupyter kernel
Multimodal outputs — captures matplotlib/plotly images back to Claude
Multi-notebook switching within one session
Built-in OpenTelemetry for observability

라이브 데모

실제 사용 모습

jupyter.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "jupyter": {
      "command": "uvx",
      "args": [
        "jupyter-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "jupyter": {
      "command": "uvx",
      "args": [
        "jupyter-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "jupyter": {
      "command": "uvx",
      "args": [
        "jupyter-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "jupyter": {
      "command": "uvx",
      "args": [
        "jupyter-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "jupyter",
      "command": "uvx",
      "args": [
        "jupyter-mcp-server"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "jupyter": {
      "command": {
        "path": "uvx",
        "args": [
          "jupyter-mcp-server"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add jupyter -- uvx jupyter-mcp-server

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: jupyter-mcp-server

How to run exploratory data analysis with Claude + Jupyter

👤 Data scientists, analysts ⏱ ~30 min intermediate

언제 쓸까: You've got a new dataset and want to poke at it without writing boilerplate cells yourself.

사전 조건

Running JupyterLab with token auth — jupyter lab --no-browser; copy the token from the URL
JUPYTER_URL + JUPYTER_TOKEN env vars — Set to your lab URL and token

흐름

Load the notebook and data

Use use_notebook to open analysis.ipynb. Insert a cell that loads ./data/events.parquet into a DataFrame named df.✓ 복사됨

→ Cell executes; df.head() preview returned
Iterate on analysis

What does the distribution of event_type look like? Plot it, show me the image.✓ 복사됨

→ Histogram image rendered in chat
Save a clean notebook

Clean the notebook: delete error cells, add markdown headers, restart-run-all to verify it runs top-to-bottom.✓ 복사됨

→ Notebook that reproduces end-to-end

결과: A publishable notebook with narrative, charts, and verified reproducibility.

함정

Kernel state drifts from notebook cell order — Use notebook_run-all-cells after edits to catch hidden-state bugs
Data files aren't visible to the kernel — Kernel's CWD is the notebook's dir, not where you started Jupyter — use absolute paths

함께 쓰기: filesystem

Self-healing notebooks with Claude and jupyter-mcp

👤 Researchers iterating on pipelines ⏱ ~45 min advanced

언제 쓸까: A long notebook fails halfway; you want the agent to fix the cell and resume rather than restart.

흐름

Run with error catching

Execute all cells in pipeline.ipynb. When a cell errors, read the traceback, fix the code, and retry before moving on.✓ 복사됨

→ Notebook continues past the first error with a fix applied
Log the fixes for review

Summarize every fix you made as markdown cells above the changed code✓ 복사됨

→ Audit trail of agent edits

결과: Pipeline completes with visible repair history.

Generate teaching notebooks from natural-language lesson outlines

👤 Educators, technical writers ⏱ ~30 min beginner

언제 쓸까: You want to produce a worked-example notebook for students or a blog post.

흐름

Outline → scaffold

From this lesson outline [paste], create lesson.ipynb with sections as markdown cells and code cells scaffolded.✓ 복사됨

→ Notebook with structure
Fill code cells and verify

Flesh out each code cell with runnable examples. Execute top-to-bottom and ensure zero errors.✓ 복사됨

→ Clean notebook students can run

결과: A teaching-ready notebook created in minutes, not hours.

조합

다른 MCP와 조합해 10배 효율

jupyter + filesystem

Move artifacts in/out of the notebook's working directory

Copy the plots saved by the notebook to ./reports/<date>/ via the filesystem MCP.✓ 복사됨

jupyter + postgres

Pull data from Postgres inside the notebook

In a new cell, use pandas.read_sql with my DB connection to load last month's events; then do EDA.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
use_notebook	path: str	Open/attach a notebook	0
list_notebooks		Find available notebooks	0
execute_cell	notebook_id, cell_index	Run a specific cell	kernel time
insert_execute_code_cell	notebook_id, code, position?	Add new code and run it	kernel time
read_cell	notebook_id, cell_index	Inspect existing cells	0
list_kernels		See what's running; find zombie kernels	0
restart_notebook	notebook_id	Reset kernel state cleanly	0

비용 및 제한

운영 비용

API 쿼터: None from MCP; Jupyter is yours to run
호출당 토큰: Outputs can be large — images and DataFrame heads especially
금액: Free (self-hosted)
팁: Use df.head() and df.info() not print(df) — full DataFrames bloat token usage

보안

권한, 시크릿, 파급범위

자격 증명 저장: JUPYTER_TOKEN in env — treat like a password; anyone with it can run code on your kernel

데이터 외부 송신: MCP talks to your Jupyter server URL only

문제 해결

자주 발생하는 오류와 해결

401 Unauthorized connecting to Jupyter

JUPYTER_TOKEN stale — copy fresh from jupyter server list

확인: curl -H 'Authorization: token <TOKEN>' $JUPYTER_URL/api

Kernel busy / never returns

Previous cell is still running. Use restart_notebook to recover; watch for infinite loops

확인: list_kernels shows state=busy

Plots don't appear in Claude

Ensure %matplotlib inline is set and you're returning the figure, not just calling plt.show() at end

대안

jupyter-mcp-server 다른 것과 비교

대안	언제 쓰나	단점/장점
nteract/papermill	You want scripted/parameterized notebook runs without interactive chat	No agent loop; batch-style
marimo	You want reactive notebooks with less hidden state	Different tool entirely; no MCP yet

jupyter-mcp-server