ipykernel-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ipykernel-mcprun a Python script to analyze the sales data"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ipykernel-mcp
An MCP server that manages an IPython kernel, allowing LLMs to execute Python code in a project's virtual environment.
Built with FastMCP and jupyter-client.
Tools
Tool | Description |
| Start a kernel using the |
| Execute code and return tagged output blocks ( |
| Retrieve remaining output for a timed-out execution. Auto-cleans up once complete |
| Send SIGINT to cancel a long-running execution without losing kernel state |
| Restart the kernel, clearing all variables and state |
| Stop the kernel and clean up resources |
| Return kernel status: running, alive, project_dir, connection_file, pending_executions, ports |
Related MCP server: venv-mcp-server
Installation
uv syncThe project directory passed to kernel_start must contain a .venv with ipykernel installed.
Usage
Run the MCP server:
ipykernel-mcpOr add it to your MCP client configuration:
{
"mcpServers": {
"ipykernel-mcp": {
"command": "uvx",
"args": ["--from", "git+https://github.com/0x0L/ipykernel-mcp", "ipykernel-mcp"]
}
}
}Monitoring
jupyter_watch can monitor kernel output (stdout, stderr, display data) in real-time in a browser:
npx github:0x0L/jupyter_watch <connection_file>The connection file path is printed by kernel_start when the kernel starts.
Development
uv sync --dev
uv run pytest tests/ -vPre-commit hooks are configured to run formatting, linting, and type checking:
uv run pre-commit installMaintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- -licenseAquality-maintenanceA Model Context Protocol server that allows LLMs to interact with Python environments, enabling code execution, file operations, package management, and development workflows.9
- FlicenseBqualityFmaintenanceAn MCP server that manages Python virtual environments using uv, allowing LLMs to reliably resolve dependencies and update virtual environments.67
- Alicense-qualityDmaintenanceAn MCP server that connects to existing IPython kernels, allowing Claude to execute code in a shared persistent environment with your IDE.2MIT
- AlicenseAqualityDmaintenanceAI-powered MCP server for connecting and managing Jupyter Notebooks. Enables interactive code execution, multi-notebook management, and multimodal output for data analysis, visualization, and machine learning.129MIT
Related MCP Connectors
MCP server for generating rough-draft project plans from natural-language prompts.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
An MCP server that gives your AI access to the source code and docs of all public github repos
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/0x0L/ipykernel-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server