What is the 'Neural Link'?

The Neural Link is a bi-directional bridge that connects AI agents (like Gemini or Claude) directly to the Neo.mjs runtime. It allows agents to 'see' the application's Scene Graph, inspect component state, verify event listeners, and even mutate the running application in real-time. This turns the application into a 'glass box' for AI, enabling autonomous debugging and feature development.

Why is Neo.mjs called an 'Application Engine' instead of a framework?

Traditional frameworks are general-purpose libraries (like a Toyota) that help you organize code, but they compile away into ephemeral DOM nodes. Neo.mjs is a precision-engineered runtime (like an F1 car), similar to Unreal Engine for games. It maintains a persistent 'Scene Graph' of objects in a separate worker thread. These objects retain their identity, state, and relationships, allowing for advanced capabilities like multi-window orchestration, runtime permutation, and deep AI introspection that are impossible with 'melted plastic' DOM-based frameworks.

What is 'Context Engineering'?

Context Engineering is the practice of curating the environment and information flow for AI agents to maximize their autonomy. In Neo.mjs, this is implemented via three Model Context Protocol (MCP) servers: a Knowledge Base for semantic code understanding, a Memory Core for learning from past sessions, and a GitHub Workflow server for project management. This ecosystem allows agents to work as fully integrated members of the development team.

What is 'Object Permanence' in the context of Neo.mjs?

In Neo.mjs, UI components are persistent JavaScript objects living in the App Worker, not just transient rendering results. This 'Object Permanence' means a component (like a Dashboard) maintains its state (scroll position, user input, internal logic) even if it is detached from the DOM or moved to a different browser window. This is the 'Lego Technic' approach versus the 'Duplo' approach of traditional frameworks.

What is an 'Agent Operating System'?

Neo.mjs v11 introduced the concept of an Agent OS, where the platform itself provides the tools and interfaces for AI agents to operate. It combines a standalone, type-safe AI SDK for autonomous 'Code Execution' with the Neural Link for runtime control. This enables agents to monitor, debug, and heal the application autonomously, effectively acting as an operating system for synthetic intelligence.

How does Neo.mjs handle multi-window applications?

Neo.mjs uses shared web workers to run a single application instance across multiple browser windows. All windows share the same application state and data in real-time. Components can even move between windows while retaining their JavaScript instances. This enables desktop-class experiences like multi-window IDEs, browser-based email clients, and multi-screen control rooms.

What makes Neo.mjs different from React, Angular, or Vue?

Neo.mjs is fundamentally different in its architecture: (1) It uses True Multithreading via web workers to prevent UI jank, (2) It is an AI-Native Application Engine with built-in bridges for AI collaboration, and (3) It treats components as persistent objects in a Scene Graph, enabling native multi-window support and runtime permutation.

Frontmatter

id	7951
title	Enhance MCP Client with Connection State and Env Validation
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Nov 30, 2025, 4:22 PM
updatedAt	Nov 30, 2025, 4:31 PM
githubUrl	https://github.com/neomjs/neo/issues/7951
author	tobiu
commentsCount	1
parentIssue	7931
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 30, 2025, 4:31 PM

Enhance MCP Client with Connection State and Env Validation

Name: Neo.mjs Application Engine
Author: Neo.mjs

Closed v11.14.0 enhancementai

tobiu commented on Nov 30, 2025, 4:22 PM

Context

A recent architectural review suggested improvements to the Neo.ai.mcp.client.Client configuration and state management.

Goal

Enhance the MCP Client with connection state tracking and environment variable validation to improve robustness and developer experience.

Requirements

Connection State: Add a connected config to Client.mjs.
- Type: Non-reactive config (class field or config without underscore, unless we identify a need for reactivity later).
- Logic: Set to true after successful connection in initAsync. Set to false in close.
- Benefit: Allows agents to check connection status before attempting operations.
Environment Validation: Add requiredEnv support to ai/mcp/client/config.mjs and Client.mjs.
- Config: Update ClientConfig schema (conceptually) to support a requiredEnv: String[] array in the server definition.
- Validation: In Client.mjs initAsync, check if the defined required environment variables exist in the env object (or process.env). Throw a descriptive error if any are missing before attempting to spawn the server process.
- Benefit: Fail-fast with clear error messages instead of cryptic spawn failures.

Deliverables

Updated ai/mcp/client/Client.mjs.
Updated ai/mcp/client/config.mjs (example/default config to include required envs for our servers, e.g., GH_TOKEN).

tobiu added the enhancement label on Nov 30, 2025, 4:22 PM

tobiu added the ai label on Nov 30, 2025, 4:22 PM

tobiu added parent issue #7931 on Nov 30, 2025, 4:22 PM

tobiu assigned to @tobiu on Nov 30, 2025, 4:22 PM

tobiu referenced in commit 5966472 - "Enhance MCP Client with Connection State and Env Validation #7951" on Nov 30, 2025, 4:31 PM

tobiu Nov 30, 2025, 4:31 PM

Input from Gemini 2.5 pro:

✦ I have successfully implemented connection state tracking and environment validation in Neo.ai.mcp.client.Client.

Changes

Configuration: Updated ai/mcp/client/config.mjs to include requiredEnv for our default servers (GH_TOKEN, GEMINI_API_KEY).

Client Enhancement:

Added connected state (boolean).

Added requiredEnv config.

Updated initAsync to validate requiredEnv against this.env (and process.env fallback) before connection.

Updated initAsync to set connected = true on success.

Updated close to set connected = false.

Updated callTool and listTools to throw if !connected.

Verification

Ran mcp-demo-agent.mjs. It connected successfully, indicating the environment checks passed (my environment has the keys). The agent output confirms the clients are operational. I verified the new state properties in the debug log.

I am ready to close this ticket.

tobiu closed this issue on Nov 30, 2025, 4:31 PM