nicegui-llm-bridge
Click on "Deploy 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., "@nicegui-llm-bridgeOpen the gallery app and click the Increment button."
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.
nicegui-llm-bridge
Drive any NiceGUI 3.x app from an LLM. No browser. No DOM. Pure wire.
v0.0.1-alpha — YOLO ship, single overnight build, only smoke-tested against the bundled examples/gallery.py and one probe against live nicegui.io. No unit tests beyond the round-trip E2E. Wire protocol is NiceGUI-3.x-specific and will break on major-version drift. Feedback from agent operators welcome — see issue #1 for the questions we'd most like answered.
This is the third member of the nicegui-tui / nicegui-wire / nicegui-llm-bridge trio. It treats NiceGUI's Client abstraction as exactly what it is — a consumer of an outbox — and adds an LLM-shaped rendering target:
nicegui-tui→ renders into a Textual TUI in-processnicegui-wire→ renders into Textual / framebuffer over the networknicegui-llm-bridge→ renders into an LLM's cognition, via MCP
What it does
Connects to a running NiceGUI page via the Socket.IO wire (reusing nicegui-wire's engine), keeps a live element-tree mirror, and exposes it to an LLM as indented bullets:
- div#3
- div#4 text='nicegui-llm-bridge gallery'
- q-tabs#6 model-value='basics' [interactive: update:modelValue]
- q-tab#7 label='Basics', name='basics'
- q-tab-panels#12 model-value='basics' [interactive: update:modelValue]
- q-tab-panel#13 name='basics'
- div#17 text='count: 0'
- q-btn#18 label='Increment' [interactive: click]
- q-btn#19 label='Warn' [interactive: click]Then the LLM can act: click(18) → page rerenders → LLM sees count: 1.
Related MCP server: Browserbeam MCP Server
MCP tools
Tool | Purpose |
| Connect to a NiceGUI page and return the indented-bullet view |
| Re-emit current mirror (no network roundtrip) |
| JSON list of every interactive element |
| Fire a click; return post-action view |
| Set a form value; return post-action view |
| Pick a radio/select option by visible label |
All element references are raw integer IDs (#18), surfaced inline so the LLM can never guess — it must read before it acts.
Why indented bullets
For tree-shaped data, indentation column = depth. No pointer chasing, no global indices to cross-reference, matches the training distribution (READMEs, file trees, doc outlines). Edge lists, JSON, and adjacency lists are all worse for LLM tree reading — see arXiv 2511.10234 (Lost in Serialization) for the empirics.
Snapshot-on-demand
The background wire connection ingests every server update into a local mirror. The LLM never sees the firehose — it only sees what read() / click() / fill() return. A ui.log tailing at 10 Hz is invisible until the LLM asks.
Try it
# 1. Set up venv + install (one-time)
python3 -m venv .venv
.venv/bin/pip install -e .
# 2. Launch the gallery (terminal A)
.venv/bin/python examples/gallery.py
# 3. Drive it (terminal B)
.venv/bin/python examples/smoke.py # CLI demo, prints transcript
.venv/bin/python tests/test_mcp_e2e.py # full MCP round-tripUse from Claude Code
Add to ~/.claude.json mcpServers (or use the bundled .mcp.json if you launch Claude Code from this repo):
{
"mcpServers": {
"nicegui-bridge": {
"command": "/Users/evnchn/nicegui-llm-bridge/.venv/bin/python",
"args": ["-m", "nicegui_llm_bridge.mcp_server"]
}
}
}Then in Claude Code: open a NiceGUI app (examples/gallery.py in another terminal), and ask Claude to drive it. Claude will call open → actions → click/fill like a screen reader would.
Architecture
NiceGUI server ──Socket.IO──> nicegui-wire (tree decode, event encode)
│
▼
ElementTree mirror
│
▼
serialize.render() → bullets
│
▼
Session (snapshot-on-demand)
│
▼
FastMCP tools (stdio)
│
▼
LLM consumerStatus
v0.0.1-alpha, YOLO-shipped 2026-06-03 ~10:30 HKT. Works against NiceGUI 3.12.x. Probed against https://nicegui.io (380 elements in 1.22 s, 15 KB YAML view, 42 actionable elements surfaced).
Known limitations:
ui.htmland arbitrary Vue components → render as opaque entries (nicegui-html#39with no inner content)ui.aggrid/ui.echart→ schema only, not dataPage navigation (multi-route apps) → not yet;
open()reconnects from scratchQuasar client-side toggles (q-drawer / q-menu burgers) don't roundtrip the wire — they live in DOM, not the outbox
q-btncontent nested innicegui-htmllooks empty to the LLM until we surfaceinnerHTML(planned)Wire protocol is NiceGUI 3.x specific; major-version drift will break
Credits
Wire decoding lifted from nicegui-wire. Gallery example adapted from nicegui-tui.
This server cannot be deployed
Maintenance
Related MCP Connectors
Give any MCP-compatible AI assistant a builder for live, hosted web tools and workflows.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Hyperbrowser MCP — wraps the Hyperbrowser AI-agent browsing API
Live browser debugging for AI assistants — DOM, console, network via MCP.
Related MCP Servers
- FlicenseBqualityDmaintenancePlaywright wrapper for MCP that enables LLM-powered clients to control a browser for automation tasks.101-
- AlicenseNot gradedqualityDmaintenanceEnables real browser automation as tools in Cursor, Claude Desktop, Windsurf, and any MCP-compatible client, allowing AI agents to interact with web pages through natural language.5 npmMIT
- AlicenseAqualityBmaintenanceProvides browser automation, audio transcription, and LLM chat as MCP tools for any agent.7MIT
- AlicenseAqualityCmaintenanceAgent-native browser control MCP server that enables AI agents to browse and interact with web pages via accessibility tree snapshots and ref ID-based commands.152MIT