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	7931
title	Epic: MCP Client Implementation for Agents
state	Closed
labels	epicai
assignees	tobiu
createdAt	Nov 29, 2025, 6:32 PM
updatedAt	Dec 1, 2025, 6:14 PM
githubUrl	https://github.com/neomjs/neo/issues/7931
author	tobiu
commentsCount	0
parentIssue	null
subIssues	7935 Feat: Implement MCP Client SDK and Demo Agent 7936 Feat: Implement MCP Client Configuration 7937 Feat: Implement MCP Client CLI and NPM Script 7938 Refactor: Standardize MCP Client CLI Filename 7939 Feat: Implement Dynamic Tool Proxies for MCP Client 7940 Feat: Add Neo.snakeToCamel utility function 7941 Investigate Multi-Server Tool Namespacing for MCP Client 7942 Feat: Enable External Configuration and Generic Runner for MCP Client CLI 7945 Refactor: MCP Client Lifecycle and CLI Runner Renaming 7946 Feat: Implement Client-Side Tool Validation in MCP Client 7949 Refactor Shared Tool Validation Service for MCP Client and Server 7950 Refactor ToolService to Class-based Architecture 7951 Enhance MCP Client with Connection State and Env Validation 7952 Fix ToolService.mjs Git Case Sensitivity Issue 7953 Refactor Client Configuration Consistency
subIssuesCompleted	15
subIssuesTotal	15
blockedBy	[]
blocking	[]
closedAt	Dec 1, 2025, 6:14 PM

Epic: MCP Client Implementation for Agents

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

Closed v11.14.0 epicai

tobiu commented on Nov 29, 2025, 6:32 PM

Context

Currently, our agents (like pm.mjs) use the "Code Execution" pattern by importing service classes directly from ai/services.mjs. This is efficient but tightly coupled to the repo structure.

To achieve true decoupling and enable agents to use any MCP server (not just ours, and not just local ones), we need to implement a standard MCP Client within our SDK.

Strategic Value

Standardization: Agents communicate via the standard MCP protocol (Stdio/SSE), making them agnostic to the server's implementation.
Extensibility: Agents can connect to 3rd-party MCP servers (e.g., a PostgreSQL MCP, a Google Drive MCP) just by spawning them.
Recursion: Agents can spawn new Agents, and those Agents can connect to the same (or different) MCP servers.

Key Deliverables

Client SDK: Implement Neo.ai.mcp.Client using @modelcontextprotocol/sdk.
- Support StdioClientTransport.
- Support dynamic tool discovery (list_tools).
Agent Integration: Update Neo.ai.Agent (future class) to accept a list of MCP Server configs, connecting to them on startup.
Demo: An agent that uses the github-workflow server via MCP protocol instead of direct import.

Tech Stack

@modelcontextprotocol/sdk

tobiu added the epic label on Nov 29, 2025, 6:32 PM

tobiu added the ai label on Nov 29, 2025, 6:32 PM

tobiu assigned to @tobiu on Nov 29, 2025, 6:32 PM

tobiu cross-referenced by #7935 on Nov 29, 2025, 11:33 PM

tobiu added sub-issue #7935 on Nov 29, 2025, 11:33 PM

tobiu added sub-issue #7936 on Nov 29, 2025, 11:45 PM

tobiu added sub-issue #7937 on Nov 29, 2025, 11:48 PM

tobiu added sub-issue #7938 on Nov 29, 2025, 11:56 PM

tobiu referenced in commit fe69334 - "Epic: MCP Client Implementation for Agents #7931" on Nov 29, 2025, 11:57 PM

tobiu added sub-issue #7939 on Nov 30, 2025, 12:03 AM

tobiu added sub-issue #7940 on Nov 30, 2025, 12:19 AM

tobiu added sub-issue #7941 on Nov 30, 2025, 12:30 AM

tobiu added sub-issue #7942 on Nov 30, 2025, 12:57 AM

tobiu added sub-issue #7945 on Nov 30, 2025, 1:50 AM

tobiu added sub-issue #7946 on Nov 30, 2025, 12:00 PM

tobiu cross-referenced by #7947 on Nov 30, 2025, 1:24 PM

tobiu added sub-issue #7949 on Nov 30, 2025, 2:51 PM

tobiu added sub-issue #7950 on Nov 30, 2025, 3:38 PM

tobiu added sub-issue #7951 on Nov 30, 2025, 4:22 PM

tobiu added sub-issue #7952 on Nov 30, 2025, 4:44 PM

tobiu added sub-issue #7953 on Nov 30, 2025, 4:58 PM

tobiu closed this issue on Dec 1, 2025, 6:14 PM