{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_zb3mtr6u2tt3","handle":"iflow-mcp-jupyter-server","url":"https://wellknown.network/agents/iflow-mcp-jupyter-server","links":{"self":"https://wellknown.network/agents/iflow-mcp-jupyter-server/record.json","html":"https://wellknown.network/agents/iflow-mcp-jupyter-server","markdown":"https://wellknown.network/agents/iflow-mcp-jupyter-server/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-jupyter-server","status":"https://wellknown.network/api/v1/agents/iflow-mcp-jupyter-server/status","claim":"https://wellknown.network/agents/iflow-mcp-jupyter-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-jupyter-server/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-jupyter-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-jupyter-server/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-jupyter-server/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-jupyter-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp-jupyter-server","summary":"A powerful MCP server for AI-driven Jupyter Notebook management and execution","description":"<div align=\"center\">\n\n<!-- omit in toc -->\n\n# 🪐 Jupyter MCP Server\n\n<img title=\"cover\" src=\"https://raw.githubusercontent.com/ChengJiale150/jupyter-mcp-server/main/assets/cover.png\" alt=\"Jupyter MCP Server\" data-align=\"center\" width=\"700\">\n\n<strong>专门为AI连接与管理Jupyter Notebook而开发的MCP服务</strong>\n\n*由 [ChengJiale150](https://github.com/ChengJiale150) 开发*\n\n[![Python](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)\n[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n[![Version](https://img.shields.io/pypi/v/better-jupyter-mcp-server.svg)](https://pypi.org/project/better-jupyter-mcp-server/)\n[![mcp-registry](https://img.shields.io/badge/mcp--registry-v1.1.0-blue)](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.ChengJiale150/jupyter-mcp-server)\n\n[English](https://github.com/ChengJiale150/jupyter-mcp-server/blob/main/README_EN.md) | 中文\n\n</div>\n\n## 📖 目录\n\n- [项目简介](#-项目简介)\n- [工具一览](#-工具一览)\n- [快速上手](#-快速上手)\n- [最佳实践](#-最佳实践)\n- [贡献指南](#-贡献指南)\n- [致谢](#-致谢)\n\n## 🎯 项目简介\n\nJupyter MCP Server 是一个基于 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) 的服务，为目前最先进的的AI IDE(如 [Cursor](https://www.cursor.com/)) 与CLI工具(如[Gemini CLI](https://github.com/google-gemini/gemini-cli))提供连接与管理Jupyter Notebook的能力。使得AI能够操作Notebook，进行数据分析、可视化、机器学习等任务。\n\n### 🤔 为什么需要Jupyter MCP Server\n\nJupyter Notebook 是数据科学家最常用的工具之一，它提供了一个交互式的环境，使其可以方便地进行数据分析、可视化、机器学习等探索性任务。然而，由于Notebook自身的格式限制，使得其难以像纯文本文件（如Markdown、Python文件）一样被AI直接理解。\n\n现有的提供操作Notebook的工具或MCP服务，要么仅能阅读与编辑Notebook，要么仅能操纵单个Notebook，难以满足同时操纵多个Notebook的复杂需求。此外，大多数工具也不支持多模态输出，无法充分利用目前最先进的多模态大模型（如Gemini 2.5）的强大图文理解能力。\n\nJupyter MCP Server 就是为了解决这个问题而开发的。它通过MCP协议，向AI提供了管理Jupyter Kernel与Notebook的工具，使其能够操纵**多个Notebook**进行**交互式**的任务执行，并输出**多模态**结果，助力数据科学家提高分析效率。\n\n### ✨ 关键亮点\n\n- 🔌 **MCP兼容**: 能够在任何支持MCP协议的IDE或CLI工具中使用\n- 📚 **多Notebook管理**: 支持同时管理多个Notebook\n- 🔁 **交互式执行**: 能够根据Cell的输出自动调整执行策略\n- 📊 **多模态输出**: 支持输出多模态结果，如文本、图片、表格等\n\n## 🔧 工具一览\n\n### Notebook管理模块\n\n| 名称            …","publisher":null,"homepage":"https://github.com/ChengJiale150/jupyter-mcp-server/blob/main/README.md","repository":"https://github.com/ChengJiale150/jupyter-mcp-server/blob/main/README.md","version":"1.4.12","license":"MIT","protocols":["mcp"],"tags":["ai","data-science","jupyter","machine-learning","mcp","model-context-protocol","notebook"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp-jupyter-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"code.execution","name":"Code Execution","confidence":1,"provenance":"declared"}],"categories":["code"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp-jupyter-server","registry":"pypi","observedAt":"2026-10-28T05:23:53.670Z","publishedAt":"2025-11-12T10:04:46.177954Z","latestVersion":"1.4.12"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp-jupyter-server","url":"https://pypi.org/project/iflow-mcp-jupyter-server/","firstSeenAt":"2026-09-09T19:24:22.327Z","fetchedAt":"2026-10-28T05:21:46.531Z","normalizedAt":"2026-10-28T05:21:46.531Z"}]},"firstSeenAt":"2026-09-09T19:24:22.327Z","updatedAt":"2026-10-28T05:23:53.670Z"}