neon3-mcp
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., "@neon3-mcp Validate this NUI Flow and submit it to Neon3"
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.
Neon3 AI Authoring MCP
Teach an AI to build Neon3 interfaces correctly, then let Neon3 prove the result.
An MCP server, detailed authoring Skill, and Python/Node starter kit for Neon3. It combines three layers:
Skill durable NUI Flow rules and design boundaries
MCP resources/tools searchable references, live capability discovery, orchestration
Neon3 runtime authoritative parser, compiler, revision, and renderer feedbackThe MCP never invents a second UI language. neon3_nui_validate invokes the
production neon-ui-runtime parser/compiler, while live mutations use the
existing length-prefixed neon3.rpc contract.
Highlights
Area | Included |
NUI Flow | V1 grammar, typed inputs, layouts, controls, events, branches, statecharts, drag/drop, world panels |
AI workflow | validate, inspect, submit, snapshots, capabilities, diagnostics |
Runtime safety | loopback RPC, request IDs, bounded app paths, fixed process profiles, timeouts |
Application code | Python and Node templates using the official Neon3 envelope |
Documentation | MCP resources plus a standalone OpenCode-compatible Skill |
Related MCP server: Flowcore Platform MCP Server
Requirements
Node.js 20 or newer.
Neon3 checked out at
D:\Neon3on Windows, orNEON3_ROOTset to another checkout.Build the Neon3 authoring probe once:
cd D:\Neon3
cargo build -p neon-ui-runtime --bin neon3_authoring_probeThe probe is the compatibility bridge between this MCP package and the exact Neon3 checkout. It returns structured JSONL and uses the same parser/compiler as the running UI runtime.
Install From Source
git clone https://github.com/unco999/neon3-ai-authoring-mcp.git
cd neon3-ai-authoring-mcp
npm install
npm linkThe command is now available as neon3-mcp.
Install From npm
Once published:
npm install -g @neon3/ai-authoring-mcp
neon3-mcpFor a pinned local install:
npm install --save-dev @neon3/ai-authoring-mcp
npx neon3-mcpOpenCode Configuration
Add an MCP entry to your OpenCode configuration:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"neon3": {
"type": "local",
"command": ["neon3-mcp"],
"enabled": true,
"environment": {
"NEON3_ROOT": "D:\\Neon3",
"NEON3_UI_ENDPOINT": "127.0.0.1:39102",
"NEON3_WGPU_ENDPOINT": "127.0.0.1:39103",
"NEON3_PROJECTD_ENDPOINT": "127.0.0.1:39104"
}
}
}
}Copy skill/SKILL.md into the host's skill directory, or add this repository
as a skill source. The Skill is separate from the MCP server so its authoring
rules remain available when Neon3 is offline.
The MCP also exposes the same material as resources:
neon3://skill
neon3://references/overview
neon3://references/grammar
neon3://references/components
neon3://references/statecharts
neon3://references/interactions
neon3://references/diagnosticsClaude Desktop / MCP Clients
{
"mcpServers": {
"neon3": {
"command": "neon3-mcp",
"env": {
"NEON3_ROOT": "D:\\Neon3",
"NEON3_UI_ENDPOINT": "127.0.0.1:39102"
}
}
}
}Tools
Tool | Purpose |
| Read a detailed authoritative syntax topic |
| Parse and compile without mutating Neon3 |
| Return canonical IR, schema, stable nodes, bindings, and budgets |
| Validate, then submit through |
| Query current service capabilities and epochs |
| Read UI state and revision information |
| Read project summary and stable |
| Correlate service snapshots and interaction traces |
| Create a bounded Python or Node application |
| Run a fixed application profile with a timeout |
| Run deterministic local application checks |
The Authoring Loop
reference -> capabilities -> generate NUI -> validate -> inspect -> submit -> diagnoseExample of valid, typed, semantic NUI:
version 1
surface surface.example revision 1
budget nodes=32 bindings=16 instances=16 text=16 glyphs=1024 events=8 clips=64
input title text default text:empty
input can_save bool default false
surface root column w 520 h 240 gap 8 pad 16
text heading value $title
button save value "Save" enabled $can_save event document.saveNUI Flow must not contain fetch, callbacks, Python code, file paths,
coordinates, GPU handles, or arbitrary expressions.
Templates
templates/python-app and templates/node-app include:
neon3.app.jsonapplication metadataui/main.nuityped declarative UIa minimal length-prefixed RPC client
a deterministic protocol test or syntax check
The neon3_app_init tool only writes below NEON3_APP_ROOT (or the current
working directory when that variable is unset).
Validate NUI Without a Live Runtime
$source = [string]::Join("`n", (Get-Content .\templates\node-app\ui\main.nui))
$request = @{ request_id = "manual-1"; operation = "validate"; sequence = 1; source = $source } | ConvertTo-Json -Compress
$request | cargo run --quiet -p neon-ui-runtime --manifest-path D:\Neon3\Cargo.toml --bin neon3_authoring_probeThe process emits JSONL. A parser or compiler failure returns exit code 1 and includes stable diagnostics and source spans.
Start Neon3 Headless Services
Use the existing Neon3 launcher. The MCP does not silently create a second renderer:
cd D:\Neon3
scripts\run-neon-services.ps1Then call neon3_capabilities, neon3_ui_snapshot, or neon3_nui_submit from
the AI client.
Configuration
Variable | Default | Meaning |
|
| Neon3 checkout used to build/run the authoring probe |
| auto | Absolute probe executable override |
|
| UI runtime RPC endpoint |
|
| WGPU runtime RPC endpoint |
|
| Project authority RPC endpoint |
| current directory | Allowed root for generated app processes |
All live endpoints must be loopback endpoints. The MCP does not expose an arbitrary shell command tool.
Troubleshooting
The authoring probe cannot start
cd D:\Neon3
cargo build -p neon-ui-runtime --bin neon3_authoring_probe
$env:NEON3_ROOT = 'D:\Neon3'revision_conflict
Call neon3_ui_snapshot, use the returned authoritative revision, and submit
again. Do not blindly retry a stale mutation.
A service is unreachable
Check the endpoint in neon3_capabilities. Start Neon3 with
scripts\run-neon-services.ps1 or use neon-dev for a windowed case.
Development
npm install
npm test
node --check src/index.js
npm pack --dry-runThe protocol test uses a deterministic local fake Neon3 endpoint and verifies
request IDs, framing, and structured JSON output. The real NUI boundary is
verified by neon3_authoring_probe in the Neon3 repository.
Project Relationship
This repository is the AI integration layer. Neon3 remains the owner of the protocol, NUI grammar, UI runtime, WGPU runtime, and project authority:
MCP:
https://github.com/unco999/neon3-ai-authoring-mcpNeon3:
https://github.com/unco999/Neon3-CiJian
License
MIT. See LICENSE.
Available Tools
11 toolsneon3_app_initB
Create a bounded Python or Node Neon3 application template. Files are written only below NEON3_APP_ROOT.
Inputs: runtime (required), destination (required), overwrite.
neon3_app_runC
Run a generated Python or Node app with a fixed executable profile and bounded timeout.
Inputs: cwd (required), runtime (required), args, entry, +1 more.
neon3_app_testA
Run the generated app's deterministic local protocol checks without contacting a live Neon3 service.
Inputs: cwd (required), runtime (required), timeout_ms.
neon3_capabilitiesC
Query service.describe from Neon3 services and return their current capabilities and epochs.
Inputs: ui_endpoint, wgpu_endpoint, projectd_endpoint.
neon3_diagnoseC
Aggregate service snapshots, UI revisions, and interaction trace for a Neon3 authoring issue.
Inputs: ui_endpoint, wgpu_endpoint, interaction_id.
neon3_nui_inspectC
Return the canonical IR, typed input schema, state machines, stable node outline, bindings, and budgets for NUI Flow.
Inputs: source (required).
neon3_nui_referenceB
Read the authoritative Neon3 NUI Flow V1 reference. Topics: overview, grammar, components, statecharts, interactions, diagnostics.
Inputs: topic (required).
neon3_nui_submitC
Validate NUI Flow locally, then submit it through ui-runtime to the WGPU runtime.
Inputs: source (required), ui_endpoint, idempotency_key, expected_revision.
neon3_nui_validateB
Parse and compile NUI Flow with Neon3's production parser/compiler. Never submit automatically.
Inputs: source (required).
neon3_project_assetsC
Read project summary and stable AssetRef entries from projectd.
Inputs: projectd_endpoint.
neon3_ui_snapshotC
Read the current UI runtime snapshot, including active fragment and input revisions.
Inputs: ui_endpoint.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool addresses a distinct stage or resource: reference docs, validation, IR inspection, submission, project assets, capabilities, UI snapshot, app template lifecycle, and diagnostics. There is no meaningful overlap, and validate/inspect/submit are clearly separated by compile, inspect, and runtime submission roles.
All tool names share the neon3_ prefix and use snake_case, which is consistent and readable. However, the set mixes noun-style names like nui_reference and ui_snapshot with verb-style names like nui_validate and app_run, so the naming pattern is not perfectly uniform.
11 tools is a well-scoped count for a Neon3 authoring/debugging server. Each tool provides a distinct capability needed for the domain without redundant or superfluous entries.
The core workflow is well covered: reference, validate, inspect, submit, create/run/test app templates, and diagnose issues. Minor gaps exist, such as no explicit update/delete for app templates and no write access to project assets, but these do not block the primary authoring flow.
Maintenance
Related MCP Connectors
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Deploy and manage Jade Hosting projects from AI clients. Jade account and OAuth required.
Build, run, inspect, and continue AgentScript workflows on connected Super Chrome and Mac clients.
Create, test, publish, and manage Dreamlit notification workflows from AI clients.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables the management of AI-powered VibeKit apps, allowing users to control deployments, monitor logs, and perform database operations directly from MCP-compatible clients. It facilitates interaction with hosted AI agents and the execution of headless coding tasks through natural language.49201 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to query and manage Flowcore resources through a structured API.10-
- AlicenseBqualityDmaintenanceConnects AI assistants to the Node-RED Admin API, enabling flow inspection, node management, graph analysis, debug capture, and rollback operations through natural language.37MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to manage Flow Relay projects, generate handoffs and insights, and interact with integrations like Discord through natural language.18359 npmAGPL 3.0