MCPgee
MCPgee
MCPgeeMCPgee

PyWry

v1.0.0•Developer Tools•stable

PyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop, web, and notebook experiences from a single API.

aggridanywidgetchat-applicationclaude-codeclaude-code-plugin
Share:
85
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is PyWry?

PyWry is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to pywry is a cross-platform app factory, rendering engine and ui toolkit for python that produces native desktop, web, and notebook experiences from a single api.

PyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop, web, and notebook experiences from a single API.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • PyWry is a cross-platform app factory, rendering engine and

Use Cases

Build cross-platform desktop and web UIs from Python with single API.
Create dashboards and chat interfaces with PyWry.
Integrate UI frameworks with Claude Code for rich visualizations.
deeleeramone

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx pywry

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use PyWry

PyWry is a cross-platform app factory, rendering engine, and UI toolkit for Python that lets you build native desktop windows, Jupyter widgets, and browser-based dashboards from a single Python API. Its MCP server exposes over 66 tools — including `create_widget`, `show_plotly`, `show_dataframe`, and `show_tvchart` — so AI assistants like Claude can render rich interactive visualizations directly in response to prompts. Developers use it to create financial dashboards, chat interfaces with streaming support, and embedded data-science UIs without switching UI frameworks.

Prerequisites

  • Python 3.10–3.14 installed in a virtual environment
  • pip or uv package manager available
  • An MCP client such as Claude Desktop or Claude Code
  • Linux users need libwebkit2gtk-4.1-dev and related system packages
  • Optional: Node.js 20+ for the Claude Code plugin marketplace install path
1

Install PyWry with MCP support

Install the PyWry package with the `mcp` extra, which includes the MCP server and all required dependencies for the stdio transport.

pip install 'pywry[mcp]'
2

Install Linux system dependencies (Linux only)

On Linux, install the required WebKit and GTK system libraries before running PyWry. Skip this step on macOS or Windows.

sudo apt-get install libwebkit2gtk-4.1-dev libgtk-3-dev libglib2.0-dev libxkbcommon-x11-0 libxcb-icccm4 libxcb-image0 libxcb-keysyms1 libxcb-randr0 libxcb-render-util0 libxcb-xinerama0 libxcb-xfixes0 libxcb-shape0 libgl1 libegl1
3

Verify the MCP server starts

Run the server manually to confirm it launches without errors before adding it to your MCP client configuration.

pywry mcp --transport stdio
4

Add PyWry to your MCP client configuration

Edit your `claude_desktop_config.json` to register the PyWry MCP server. The server is launched via the `pywry` CLI with stdio transport.

5

Restart your MCP client and verify tools

Restart Claude Desktop (or your MCP client) and ask Claude to list available PyWry tools. You should see tools like `show_plotly`, `show_dataframe`, and `create_chat_widget`.

PyWry Examples

Client configuration

Add this block to your `claude_desktop_config.json` to register the PyWry MCP server using stdio transport.

{
  "mcpServers": {
    "pywry": {
      "command": "pywry",
      "args": ["mcp", "--transport", "stdio"]
    }
  }
}

Prompts to try

Once connected, use these prompts to exercise PyWry's visualization and UI capabilities.

- "Show me a Plotly bar chart of monthly sales figures using the show_plotly tool."
- "Display this pandas DataFrame as an interactive table in a native window."
- "Create a TradingView-style chart for AAPL with candlestick data."
- "Open a chat widget with streaming support in a new desktop window."

Troubleshooting PyWry

Server crashes on Linux with a WebKit or GTK error

Ensure all system dependencies are installed: `sudo apt-get install libwebkit2gtk-4.1-dev libgtk-3-dev libglib2.0-dev`. Check with `apt list --installed | grep webkit`.

`pywry` command not found after installation

Make sure you are in the correct virtual environment (`source .venv/bin/activate`) and that you installed `pywry[mcp]`, not just `pywry`. Run `pip show pywry` to confirm the install.

No tools appear in the MCP client after adding the server

Confirm the server launches cleanly by running `pywry mcp --transport stdio` in a terminal. Check that the `command` field in `claude_desktop_config.json` points to the correct `pywry` binary (use `which pywry` to verify the path).

Frequently Asked Questions about PyWry

What is PyWry?

PyWry is a Model Context Protocol (MCP) server that pywry is a cross-platform app factory, rendering engine and ui toolkit for python that produces native desktop, web, and notebook experiences from a single api. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install PyWry?

Follow the installation instructions on the PyWry GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with PyWry?

PyWry works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is PyWry free to use?

Yes, PyWry is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

PyWry Alternatives — Similar Developer Tools Servers

Looking for alternatives to PyWry? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "pywry": { "command": "npx", "args": ["-y", "pywry"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use PyWry?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides