Jupyter Notebook Bridge
The Jupyter MCP Server provides a bridge between AI assistants and Jupyter notebooks, enabling models to programmatically create and execute code cells, add markdown content, and interact with Earth data through specialized tools. Built using the MCP protocol with both stdio and SSE transport options, it leverages the jupyter_kernel_client and jupyter_nbmodel_client libraries to manipulate notebook content and execute code in a running kernel. This implementation is particularly valuable for data science workflows where AI assistants need to generate executable code, document analysis with markdown, or facilitate Earth data retrieval and processing within Jupyter environments.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/bitrsky/jupyter_mcp_server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Jupyter Notebook Bridge from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.