✨ panel-live-server

Panel Live Server is a local Panel web server and MCP server that executes Python code snippets and renders the resulting visualizations as live, interactive web pages — enabling humans and AI assistants to display and inspect Python outputs in real time.

Features

• Two interfaces — pls serve (standalone browser UI) and pls mcp (MCP server for AI assistants)
• Any visualization library — hvplot · plotly · altair · matplotlib · seaborn · holoviews · bokeh · and more
• Validate before render — show runs syntax, security, package, and extension checks before any rendering happens
• Visual validation — screenshot MCP tool lets the AI inspect the rendered output visually before presenting it, and returns the snippet's stdout plus any browser console errors alongside the image
• Read a value, skip the picture — evaluate MCP tool runs code in the server environment and returns its text output, so the AI can check a fact without launching a browser
• Persistent storage — SQLite database with full-text search; every snippet gets its own permanent URL
• Auto-restart — Panel subprocess is health-monitored and automatically restarted on failure
• Works everywhere — local, JupyterHub, GitHub Codespaces; URLs externalized automatically

Installation

Install via uv, pip, or pixi — see the Installation guide for full instructions including how to find your pls path.

uv tool install "panel-live-server[pydata]"

Pin your version — this project is in its early stages. Pin to a specific version to avoid unexpected changes: uv tool install "panel-live-server[pydata]==0.1.0a1"

Connect to your AI assistant

Use the absolute path printed by which pls above — not just pls. Full setup instructions for each client: docs → Connect to your MCP client

Usage

$ pls

 Usage: pls [OPTIONS] COMMAND [ARGS]...

 Panel Live Server - Execute and visualize Python code snippets.

╭─ Options ────────────────────────────────────────────────────────────────────────────────────────────╮
│ --version  -V        Show version and exit.                                                          │
│ --help               Show this message and exit.                                                     │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─ Commands ───────────────────────────────────────────────────────────────────────────────────────────╮
│ serve   Start the Panel Live Server directly.                                                        │
│ mcp     Start as an MCP server for AI assistants.                                                    │
│ status  Check whether the Panel server is running.                                                   │
│ list    List resources (packages, etc.).                                                             │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────╯

You can also use panel-live-server but pls is shorter and easier to remember.

Security

Panel Live Server executes arbitrary Python. That is its purpose — show, screenshot, and evaluate all run code you or an AI assistant supplied, in the Panel server process, with the full privileges of the user who started it. It can read and write your files and reach the network exactly as any script you ran yourself could.

The validation show performs — syntax, a blocked-import list, ruff's security rules, package availability — is a guardrail, not a sandbox. It catches the plausible mistakes an assistant makes and refuses obviously inappropriate imports. It is not a security boundary and cannot be relied on as one.

So:

• Run pls only in an environment you would be willing to run arbitrary code in.
• Don't expose the server's port to an untrusted network. It has no authentication; anyone who can reach /api/snippet or /api/evaluate can execute code in that environment.
• Treat a shared or production machine as the wrong place for it.

Development

See the Contributing guide for the full setup (fork, install, connect to MCP client, run tests).

❤️ Contributing

Contributions are welcome! Please follow these steps:

1. Fork the repository.
2. Create a new branch: git checkout -b feature/YourFeature.
3. Make your changes and commit them: git commit -m 'Add some feature'.
4. Push to the branch: git push origin feature/YourFeature.
5. Open a pull request.

Please ensure your code passes all tests and linting before submitting.