MCPHub LabRegistrymicrosoft/magentic-ui
microsoft

microsoft/magentic ui

Built by microsoft • 9,745 stars

What is microsoft/magentic ui?

A high-performance MCP server implementation for microsoft/magentic-ui that bridges the gap between the Model Context Protocol and external services. It allows Large Language Models to interact with your data and tools with low latency and native support.

How to use microsoft/magentic ui?

1. Ensure you have an MCP-compatible client (like Claude Desktop) installed. 2. Configure your server with: npx @modelcontextprotocol/microsoft/magentic-ui 3. Restart your client and verify the new tools are available in the system catalog.
🛡️ Scoped (Restricted)
npx @modelcontextprotocol/microsoft-magentic-ui --scope restricted
🔓 Unrestricted Access
npx @modelcontextprotocol/microsoft-magentic-ui

Key Features

Native MCP Protocol Support
High-performance Data Streaming
Type-safe Tool Definitions
Seamless Environment Integration

Optimized Use Cases

Connecting external databases to AI workflows
Automating workflow tasks via natural language
Augmenting developer productivity with specialized tools

microsoft/magentic ui FAQ

Q

What is an MCP server?

MCP is an open standard that enables developers to build secure, two-way integrations between AI models and local or remote data sources.

Q

Is this server ready for production?

Yes, this server follows standard MCP security patterns and tool-restricted access.

Official Documentation

View on GitHub
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/_assets/magentic-lite-logo-dark.png"> <img src="docs/_assets/magentic-lite-logo-light.png" alt="MagenticLite" width="420"> </picture> </p> <p align="center"> <em>Big tasks. Small models.</em> </p>

MagenticLite is the next generation of Magentic-UI — an agentic application from Microsoft AI Frontiers, redesigned to do more with less. It pairs an on-device-friendly orchestrator model (MagenticBrain) with a specialized browser-use model (Fara) so you can automate real work without depending on frontier-scale compute.

  • Built for small models, efficient by design. Strong agentic performance without heavy compute — no frontier-scale models required.
  • Works across the browser and your local file system. Web research, form filling, file management — in one workflow.
  • Keeps you in the loop and in control. Steer, approve, or take over at any point. MagenticLite stops and checks in before taking critical actions.
  • Safe by design. Browser sessions run inside a lightweight VM sandbox (Quicksand) so the agent can't reach the rest of your machine without your say-so.

See it in action

Click any task below to expand and watch MagenticLite handle it end to end.

<details open> <summary><b>Fill expense forms</b></summary>

https://github.com/user-attachments/assets/a982b60d-127e-4310-96e6-9f094dffb7f0

</details> <details> <summary><b>Find prices for recipe ingredients</b></summary>

https://github.com/user-attachments/assets/7ff87917-752f-4e40-b319-8036e08ab8f9

</details> <details> <summary><b>Find and book a restaurant</b></summary>

https://github.com/user-attachments/assets/ee5f967e-ee1b-4554-b329-36b56b595aa4

</details> <details> <summary><b>Organize local files</b></summary>

https://github.com/user-attachments/assets/aff385dd-f856-4db4-8f26-08fd0f940aa4

</details>

Quick start

These steps get you running on macOS or Windows (WSL). Need more detail or a different platform? See the Installation Guide.

1. Install MagenticLite

# Create a project directory
mkdir magentic-lite && cd magentic-lite

# Create and activate a virtual environment
uv venv --python=3.12 --seed .venv
source .venv/bin/activate

# Install the latest 0.2.x release from PyPI
uv pip install "magentic_ui>=0.2.0"

2. Run

magentic-ui --port 8081

Open http://127.0.0.1:8081/ and follow the in-app onboarding to connect a model endpoint. If you don't have one yet, see the Model Hosting Guide.

Looking for the previous Magentic-UI 0.1 release (optimized to run with frontier models)? It lives on the magentic-ui-0.1 branch.

Documentation

DocWhat's in it
InstallationSupported platforms, macOS / WSL prerequisites, install + run commands
Build from sourceHow to run MagenticLite from a clone of this repo (uv sync, pnpm dev, etc.)
Model hosting guideEnd-to-end walkthrough of standing up a model endpoint and connecting MagenticLite to it
ConfigurationSandbox, agent mode, tool approval, full config.yaml example
TroubleshootingCommon errors and how to fix them
LimitationsTasks and usage patterns MagenticLite doesn't handle well today
Transparency NoteIntended uses, responsible-use guidance, risks, and mitigations

License

Microsoft, and any contributors, grant you a license to any code in the repository under the MIT License. See the LICENSE file.

Microsoft, Windows, Microsoft Azure, and/or other Microsoft products and services referenced in the documentation may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries. The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks. Microsoft's general trademark guidelines can be found at http://go.microsoft.com/fwlink/?LinkID=254653.

Any use of third-party trademarks or logos are subject to those third-party's policies.

Privacy information can be found at https://go.microsoft.com/fwlink/?LinkId=521839.

Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents, or trademarks, whether by implication, estoppel, or otherwise.

Global Ranking

7.6
Trust ScoreMCPHub Index

Based on codebase health & activity.

Manual Config

{ "mcpServers": { "microsoft-magentic-ui": { "command": "npx", "args": ["microsoft-magentic-ui"] } } }