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	7498
title	Fix Gemini CLI Client Compatibility for MCP `tools/list` Response
state	Closed
labels	bugai
assignees	tobiu
createdAt	Oct 15, 2025, 3:41 PM
updatedAt	Oct 15, 2025, 3:42 PM
githubUrl	https://github.com/neomjs/neo/issues/7498
author	tobiu
commentsCount	0
parentIssue	7477
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Oct 15, 2025, 3:42 PM

Fix Gemini CLI Client Compatibility for MCP `tools/list` Response

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

Closed v11.0.0 bugai

tobiu commented on Oct 15, 2025, 3:41 PM

The Gemini CLI client was unable to correctly parse the tools/list response from the neo-github-workflow MCP server due to strict validation rules and issues with npm run output. This ticket addresses these compatibility issues by adjusting the server's response format and startup command.

Acceptance Criteria

The command and args for neo-github-workflow in .gemini/settings.json are updated to directly invoke node ai/mcp/server/github-workflow/mcp-stdio.mjs, eliminating extraneous npm run output.
toolService.mjs is modified to ensure that outputSchema is always a valid JSON Schema object, even for primitive types or when no schema is explicitly defined, by wrapping primitive types in an object schema and returning an empty object schema for undefined outputs.
toolService.mjs is modified to omit the nextCursor field entirely from the listTools response when its value is null.
mcp-stdio.mjs is modified to conditionally include nextCursor in the tools/list response only if it is not undefined.
The Gemini CLI client successfully lists all tools from the neo-github-workflow server without errors.

tobiu assigned to @tobiu on Oct 15, 2025, 3:41 PM

tobiu added parent issue #7477 on Oct 15, 2025, 3:41 PM

tobiu added the bug label on Oct 15, 2025, 3:41 PM

tobiu added the ai label on Oct 15, 2025, 3:41 PM

tobiu referenced in commit 933919f - "Fix Gemini CLI Client Compatibility for MCP tools/list Response #7498" on Oct 15, 2025, 3:42 PM

tobiu closed this issue on Oct 15, 2025, 3:42 PM

tobiu cross-referenced by #7652 on Oct 25, 2025, 7:52 PM