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	9563
title	Modularize MCP Server Architecture and Extract Shared Services
state	Closed
labels	enhancementairefactoringarchitecture
assignees	tobiu
createdAt	Mar 26, 2026, 4:04 PM
updatedAt	Mar 26, 2026, 4:11 PM
githubUrl	https://github.com/neomjs/neo/issues/9563
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Mar 26, 2026, 4:11 PM

Modularize MCP Server Architecture and Extract Shared Services

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

Closed v12.1.0 enhancementairefactoringarchitecture

tobiu commented on Mar 26, 2026, 4:04 PM

Goal

Refactor the MCP server root files (Server.mjs) to reduce bloat by extracting optional and complex logic into dedicated services.

Context

With the recent addition of OIDC/OAuth 2.1 discovery, token verification, and CORS support, the Server.mjs files for Knowledge Base and Memory Core have become less readable. Since this logic is identical across servers, it should be extracted into shared services.

Proposed Changes

Extract Auth Logic: Create ai/mcp/server/shared/services/AuthService.mjs to handle OIDC discovery, token verification, and Protected Resource Metadata.
Extract SSE Logic: Create ai/mcp/server/shared/services/TransportService.mjs to manage Express apps, CORS, SSE transport handshakes, and session management.
Modular Server: Update Server.mjs to use dynamic imports for these services, keeping the root file lean and ensuring dependencies are only loaded when needed.
Consolidate Common Logic: Ensure that future MCP servers can leverage these same services for rapid and consistent deployment.

This refactoring will improve maintainability and simplify the implementation of future features like the Neural Link authorization.

tobiu added the enhancement label on Mar 26, 2026, 4:04 PM

tobiu added the ai label on Mar 26, 2026, 4:04 PM

tobiu added the refactoring label on Mar 26, 2026, 4:04 PM

tobiu added the architecture label on Mar 26, 2026, 4:04 PM

tobiu referenced in commit 8b4254a - "Modularize MCP server architecture and extract shared services (#9563)" on Mar 26, 2026, 4:11 PM

tobiu assigned to @tobiu on Mar 26, 2026, 4:11 PM

tobiu closed this issue on Mar 26, 2026, 4:11 PM

tobiu Mar 26, 2026, 4:11 PM

Refactored Server.mjs by extracting OIDC/OAuth and SSE transport logic into shared AuthService and TransportService. Improved maintainability and reduced root file bloat. Verified with functional tests.

tobiu referenced in commit cd957a3 - "Apply Anchor & Echo strategy to MCP services and tests (#9563)" on Mar 26, 2026, 4:15 PM