Jupyters - AI Notebook Assistant
🎉 Let's keep Jupyter fun!
Give your AI assistant deep, semantic access to Jupyter notebooks through the Model Context Protocol (MCP).
What is Jupyters?
Jupyters is a commercial-grade MCP server that allows AI assistants (Claude, ChatGPT, Cursor, etc.) to:
- 📓 Read and write notebook cells
- ⚡ Execute code in live Jupyter kernels
- 🔍 Inspect variables with semantic understanding (DataFrames, tensors, etc.)
- 🧠 Auto-analyze errors with variable context
- 📊 Capture plots and image outputs
- 🛡️ Prevent destructive operations with safety checks
Quick Start
1. Install
pip install jupyters-server
2. Configure Your AI Tool
For Claude Desktop:
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"jupyters": {
"command": "jupyters-server"
}
}
}
For Claude Code or other MCP clients: See documentation.
3. Restart Your AI Tool
Quit and reopen Claude Desktop (or your AI client).
4. Try It!
Ask your AI:
What Jupyter tools do you have access to?
Then:
Read my notebook at /path/to/notebook.ipynb and execute the first 3 cells
Features
| Feature | Free | Pro ($9/mo) | Team ($29/mo) |
|---|---|---|---|
| Read/Write Cells | ✅ | ✅ | ✅ |
| Execute Cells | 5/day | Unlimited | Unlimited |
| Variable Inspection | ❌ | ✅ | ✅ |
| Plot/Image Capture | ❌ | ✅ | ✅ |
| Domain Profiles (ML/Finance) | ❌ | ❌ | ✅ |
| Auto-Error Analysis | ✅ | ✅ | ✅ |
| Safety Checks | ✅ | ✅ | ✅ |
MCP Tools
Jupyters provides 16 MCP tools for notebook operations:
Notebooks: read_notebook, create_notebook, read_notebook_outline
Cells: read_cell, update_cell, add_cell, split_cell, merge_cells
Execution: run_cell, restart_kernel, get_execution_order
Inspection: inspect_variable, read_variable_sample (Pro+)
Config: set_profile (Team), activate_license, get_server_info
Upgrade
Get unlimited executions and advanced features:
# Visit https://jupyters.fun/pricing to get your license key
# Then activate via your AI:
Ask your AI: "Activate my Jupyters license: CE-PRO-XXXXXXXXXX"
Documentation
- 📖 Full docs: https://jupyters.fun/docs
- 💰 Pricing: https://jupyters.fun/pricing
- 🐛 Issues: https://github.com/jupytersfun/jupyters/issues
- 💬 Support: mbu@researchshop.pl
Requirements
- Python 3.10+
- Jupyter kernel (ipykernel)
- MCP-compatible AI client
License
Commercial software with free tier. See pricing for details.
Let's keep Jupyter fun! 🎉
Metadata
Release files for jupyters-server 0.2.0
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 |
|---|---|---|---|---|
| jupyters_server-0.2.0.tar.gz | 165.1 kB | Without provenance | Details for jupyters_server-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| jupyters_server-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for jupyters_server-0.2.0-py3-none-any.whl |
Total release size: 195.4 kB
Release files / jupyters_server-0.2.0.tar.gz
| Download URL | jupyters_server-0.2.0.tar.gz |
|---|---|
| Size | 165.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b94eb5373287ab21641366dd717412f671e963f09eaac665cb87644dd5bdfc1d
|
|
BLAKE2b-256 checksum How to use checksums |
62d40a0c37c1f44cc78383fbbbedb0d244ad09da31d4016178bf522c13a7f7b2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Release files / jupyters_server-0.2.0-py3-none-any.whl
| Download URL | jupyters_server-0.2.0-py3-none-any.whl |
|---|---|
| Size | 30.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c2f17d4978c09a10c923ad9e2a6bcb636fd24fcf26e50a86400ec6439133bbb0
|
|
BLAKE2b-256 checksum How to use checksums |
c07dee036389b9b1e9945961ba35d94501bcf57600c277360fea8ffbd2ca69cc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Security for jupyters-server 0.2.0
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.