What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

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

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	7872
title	Refactor GitHub Workflow MCP Server to use Neo.core.Base architecture
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Nov 23, 2025, 11:39 AM
updatedAt	Nov 23, 2025, 11:58 AM
githubUrl	https://github.com/neomjs/neo/issues/7872
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Nov 23, 2025, 11:58 AM

Refactor GitHub Workflow MCP Server to use Neo.core.Base architecture

Closed v11.9.0/archive-v11-9-0-chunk-1 enhancementai

tobiu commented on Nov 23, 2025, 11:39 AM

Objective: Refactor the GitHub Workflow MCP server entry point to align with the Neo.mjs architecture by encapsulating the server logic within a Neo.core.Base class.

Changes:

Create ai/mcp/server/github-workflow/Server.mjs:
- Define class Server extends Neo.core.Base.
- Class Fields: configFile, mcpServer, transport.
- initAsync():
  - Call super.initAsync().
  - Load custom config via aiConfig.load() if this.configFile is set.
  - Initialize McpServer instance.
  - Set up request handlers (listTools, callTool).
  - Perform HealthService.healthcheck() and log status.
  - Specific Logic: If health check passes, call RepositoryService.fetchAndCacheViewerPermission() to cache permissions early.
  - Initialize and connect StdioServerTransport.
- Methods: Extract helper methods for setupRequestHandlers and logStartupStatus.
Refactor ai/mcp/server/github-workflow/mcp-stdio.mjs:
- Convert into a lightweight "runner" script.
- Imports: Ensure correct order: Neo -> core/_export -> InstanceManager -> aiConfig -> logger -> Server.
- Logic:
  - Parse CLI arguments (-d, -c).
  - Update aiConfig.data.debug immediately.
  - Instantiate Server inside a try/catch block.
  - Use top-level await to wait for server.ready().
  - Handle errors cleanly (log and exit).

Technical Details:

Completes the refactoring of all 3 MCP servers to the Neo.mjs class architecture.

tobiu Nov 23, 2025, 11:44 AM

Input from Gemini:

✦ Refactoring complete. The GitHub Workflow MCP server now uses the standardized Neo.core.Base architecture.

Implementation Details:

Server.mjs: Encapsulates the server application logic, including specific GitHub permission caching in initAsync.

mcp-stdio.mjs: Converted to the standard runner pattern with robust top-level await error handling and correct import ordering.

This unifies the architecture across all three MCP servers (Memory Core, Knowledge Base, GitHub Workflow), making them easier to maintain and test.