Notebook MCP
Notebook MCP is a Model Context Protocol (MCP) server that provides deep semantic understanding of Jupyter notebooks for AI assistants and automation workflows.
🧠 Why Notebook MCP?
Jupyter notebooks are difficult for AI assistants to reason about because they are:
- Stateful
- Non-linear
- Execution-order dependent
- Mixed with outputs and markdown
Notebook MCP solves this by building execution graphs and runtime awareness.
✨ Features
- Static notebook dependency analysis
- Execution state detection (stale / unexecuted cells)
- Rerun planning engine
- Focused notebook context generation
- Notebook to deterministic Python conversion
- Jupyter kernel runtime execution and inspection
📦 Installation
pip install notebook-mcp
🚀 Running Server
notebook-mcp-python
🔧 Environment Variables (Optional)
For Jupyter runtime integration:
JUPYTER_BASE_URL=http://localhost:8888
JUPYTER_TOKEN=<your_token>
🧪 Example Use Cases
- AI notebook debugging
- Automated notebook refactoring
- Execution dependency tracking
- Runtime variable inspection
🧩 Integration
Notebook MCP is designed to integrate with:
- AI coding assistants
- MCP clients
- Notebook automation workflows
📚 Source Code
GitHub: https://github.com/akram-side-projects/notebook-mcp
🤝 Contributions
PRs and feedback welcome.
Metadata
Release files for notebook-mcp 1.5.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| notebook_mcp-1.5.5.tar.gz | 18.5 kB | Without provenance | Details for notebook_mcp-1.5.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| notebook_mcp-1.5.5-py3-none-any.whl | Python 3 | none | any | Details for notebook_mcp-1.5.5-py3-none-any.whl |
Total release size: 37.1 kB
Release files / notebook_mcp-1.5.5.tar.gz
| Download URL | notebook_mcp-1.5.5.tar.gz |
|---|---|
| Size | 18.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3e23e21afd6747f12e681a5efe5d80b4d76b62f9ba016a8dd5ff0ce15b7467fb
|
|
BLAKE2b-256 checksum How to use checksums |
d704a6c373a5b363d94f8aa1212597c45711b6920ddb2df690bd8a59f7c0f535
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.0
|
Release files / notebook_mcp-1.5.5-py3-none-any.whl
| Download URL | notebook_mcp-1.5.5-py3-none-any.whl |
|---|---|
| Size | 18.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c8c487324448e6eb8e83a8bc99fa9cc716d9e955d6bbd0485b99e0b5bbfcca57
|
|
BLAKE2b-256 checksum How to use checksums |
3590f88f0ab0bc83c19e7a42a62a37a23807afb673370e112160119bfe86a6c1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.0
|
Security for notebook-mcp 1.5.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.