{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_dnh76zzw5fpg","handle":"jupyter-mcp-live","url":"https://wellknown.network/agents/jupyter-mcp-live","links":{"self":"https://wellknown.network/agents/jupyter-mcp-live/record.json","html":"https://wellknown.network/agents/jupyter-mcp-live","markdown":"https://wellknown.network/agents/jupyter-mcp-live/record.md","api":"https://wellknown.network/api/v1/agents/jupyter-mcp-live","status":"https://wellknown.network/api/v1/agents/jupyter-mcp-live/status","claim":"https://wellknown.network/agents/jupyter-mcp-live/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/jupyter-mcp-live/claim.json","badge":"https://wellknown.network/agents/jupyter-mcp-live/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/jupyter-mcp-live/history","tools":"https://wellknown.network/api/v1/agents/jupyter-mcp-live/tools"},"ard":{"identifier":"urn:air::server:jupyter-mcp-live","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"jupyter-mcp-live","summary":"MCP server built into Jupyter Server: AI agents edit and run the notebooks open in JupyterLab, with outputs streaming into cells live.","description":"# Jupyter MCP Live\n\nA powerful MCP (Model Context Protocol) server for executing code in Jupyter notebooks. This extension enables AI assistants and other MCP clients to programmatically create, modify, and execute code across multiple kernel types (Python, R, Julia, and more) through a running Jupyter Server.\n\n## Overview\n\nJupyter MCP Live provides a comprehensive toolkit for AI-assisted coding workflows. It enables AI assistants to:\n\n- **Execute code** in any Jupyter kernel (Python, R, Julia, etc.)\n- **Create and modify** notebook cells programmatically\n- **Manage kernels** - start, stop, switch between different kernel types\n- **Query notebooks** - read cells, view outputs, check execution status\n- **Install packages** directly into kernel environments\n\nPerfect for building AI-powered data analysis tools, automated notebook workflows, and interactive coding assistants.\n\n## Key Features\n\n- **Multi-Kernel Support**: Execute code in Python, R, Julia, and any Jupyter-supported kernel\n- **Collaborative Editing**: Full support for YDoc - works seamlessly when notebooks are open in JupyterLab\n- **Live Output Streaming**: Outputs render in JupyterLab as the kernel emits them - watch long-running cells progress in real time instead of waiting for the tool call to finish\n- **Progress Notifications**: Long-running cells send MCP progress updates to the client (elapsed time, output count, latest output line), including heartbeats for silent cells\n- **Kernel Management**: Automatic kernel reuse, smart kernel resolution, and session management\n- **Complete Notebook Control**: Create, read, update, and delete cells programmatically\n- **Output Filtering**: Intelligent filtering of large outputs to optimize token usage\n- **Plots the Model Can See**: `view_cell_image` returns a cell's PNG/JPEG figures, or a markdown cell's pasted images, as MCP image content, also from inside Code Mode scripts\n- **MCP Protocol**: Standard MCP interface for AI assistant integration\n- **Authenticat…","publisher":null,"homepage":"https://github.com/zqfang/jupyter-mcp-live","repository":"https://github.com/zqfang/jupyter-mcp-live/issues","version":"0.6.2","license":"BSD 3-Clause License\n        \n        Copyright (c) 2025, jupyt…","protocols":["mcp"],"tags":["code","execution","fastmcp","jupyter","kernels","mcp"],"pricing":null,"endpoints":[{"url":"pypi:jupyter-mcp-live","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":"jupyter-mcp-live","registry":"pypi","observedAt":"2026-10-30T19:26:57.759Z","publishedAt":"2026-10-22T18:56:40.103816Z","latestVersion":"0.6.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"jupyter-mcp-live","url":"https://pypi.org/project/jupyter-mcp-live/","firstSeenAt":"2026-10-18T16:29:09.936Z","fetchedAt":"2026-10-30T19:26:01.670Z","normalizedAt":"2026-10-30T19:26:01.670Z"}]},"firstSeenAt":"2026-10-18T16:29:09.936Z","updatedAt":"2026-10-30T19:26:57.759Z"}