NiceGUI MCP
NiceGUI MCP is a docs-first Model Context Protocol server for local NiceGUI development, providing guidance lookup, code analysis, safe fixes, and starter pattern generation.
README
NiceGUI MCP
NiceGUI MCP is a docs-first Model Context Protocol server for local NiceGUI development. It bundles curated guidance, searches that guidance, analyzes pasted NiceGUI code for common problems, applies a narrow safe fixer set, and generates starter patterns for real app workflows.
What It Does
- Guidance lookup for common NiceGUI problem areas
- Topic search across bundled docs
- Static analysis for layout, scrolling, async, dialog, styling, and architecture issues
- Deterministic safe fixes for a small allowlisted set of patterns
- Starter generation for layout shells, dialogs, async flows, forms, tables, and controller/service splits
What It Does Not Do
- repo-wide indexing
- arbitrary code execution
- browser automation
- embeddings or vector search
- hosted multi-user deployment
- large-scale automated refactors
Bundled Topics
layout_spacing_scrollingasync_tasks_performancestyling_themingdialogsstate_managementcomponent_architectureforms_validationdata_views_tables_chartstestingdeployment_runtime
Tools
list_topics()get_guidance(topic)search_guidance(query, topics=None)analyze_nicegui_code(code, focus=None, filename=None, context=None)fix_nicegui_code(code, aggressive=False)generate_nicegui_component(kind, mode='default', details_json=None)
Resources
nicegui://topics/indexnicegui://guidance/{topic}
Recommended Workflow
- Search or read guidance for the problem area.
- Analyze the relevant NiceGUI snippet.
- Apply safe fixes where the fixer set supports them.
- Reanalyze the updated code.
- Generate a better pattern when the issue is architectural rather than local.
Installation
uv sync
Run
uv run nicegui-mcp
Test
uv run pytest -q
Example MCP Client Config
{
"mcpServers": {
"nicegui-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/nicegui-mcp", "nicegui-mcp"]
}
}
}
Project Layout
nicegui_mcp/
├── analyzers.py
├── docs/
├── fixers.py
├── generators.py
├── models.py
├── profile.py
├── registry.py
└── server.py
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.