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	7939
title	Feat: Implement Dynamic Tool Proxies for MCP Client
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Nov 30, 2025, 12:03 AM
updatedAt	Nov 30, 2025, 12:11 AM
githubUrl	https://github.com/neomjs/neo/issues/7939
author	tobiu
commentsCount	1
parentIssue	7931
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 30, 2025, 12:11 AM

Feat: Implement Dynamic Tool Proxies for MCP Client

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

Closed v11.14.0 enhancementai

tobiu commented on Nov 30, 2025, 12:03 AM

This task aims to enhance the MCP Client by implementing Dynamic Tool Proxies. After connecting to an MCP server, the client will expose the server''s tools as directly callable methods under a client.tools namespace. This improves ergonomics, discovery, and enables future argument validation.

Deliverables

Dynamic Tool Proxy Implementation: Enhance Neo.ai.mcp.client.Client to:
- Fetch the list of tools from the connected MCP server (using listTools()).
- Dynamically create proxy methods on a client.tools object for each discovered tool.
- Each proxy method will automatically call client.callTool() with the correct tool name and passed arguments.
Demo Agent Update: Modify ai/agents/mcp-demo-agent.mjs to demonstrate using the new client.tools.<toolName>() syntax.
Argument Validation (Optional/Future): (Consider for later) Integrate OpenAPI schemas from listTools() to perform client-side argument validation before making the callTool request.

tobiu assigned to @tobiu on Nov 30, 2025, 12:03 AM

tobiu added the enhancement label on Nov 30, 2025, 12:03 AM

tobiu added the ai label on Nov 30, 2025, 12:03 AM

tobiu added parent issue #7931 on Nov 30, 2025, 12:03 AM

tobiu referenced in commit d90957a - "Feat: Implement Dynamic Tool Proxies for MCP Client #7939" on Nov 30, 2025, 12:10 AM

tobiu Nov 30, 2025, 12:11 AM

Input from Gemini 2.5:

✦ I have implemented Dynamic Tool Proxies for the MCP Client.

Deliverables Completed

Dynamic Tool Proxy Implementation: Enhanced Neo.ai.mcp.client.Client to dynamically create proxy methods on a client.tools object for each discovered tool. Tool names are converted from snake_case to camelCase for ergonomic access.

Demo Agent Update: Modified ai/agents/mcp-demo-agent.mjs to successfully use the new client.tools.<toolName>() syntax (e.g., ghClient.tools.listIssues()).

tobiu closed this issue on Nov 30, 2025, 12:11 AM