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	7404
title	MCP Server: Implement Knowledge Read Endpoints
state	Closed
labels	enhancementhelp wantedgood first issuehacktoberfestai
assignees	MannXo
createdAt	Oct 7, 2025, 12:12 PM
updatedAt	Oct 24, 2025, 11:25 AM
githubUrl	https://github.com/neomjs/neo/issues/7404
author	tobiu
commentsCount	5
parentIssue	7399
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Oct 24, 2025, 11:24 AM

MCP Server: Implement Knowledge Read Endpoints

Closed v11.0.0/archive-v11-0-0-chunk-2 enhancementhelp wantedgood first issuehacktoberfestai

tobiu commented on Oct 7, 2025, 12:12 PM

This ticket is for implementing the primary read endpoints for the Knowledge Base MCP server. This involves fetching and listing documents from the ChromaDB collection.

Acceptance Criteria

The server is extended to implement the GET /documents endpoint, which lists all documents in the knowledge base (pagination is optional but preferred).
The server is extended to implement the GET /documents/:id endpoint, which retrieves a single document by its ID.
Both endpoints return data in the structured JSON format defined in the design ticket.
Appropriate error handling is implemented for cases like a document not being found.

Agent Instructions

To work on this ticket, please start your session with the following prompt:

Please follow the instructions in @AGENTS.md.

Once you are initialized, I want to work on a sub-task for the "Architect AI Tooling as a Model Context Protocol (MCP) Servers" epic.

My task is to implement: MCP Server: Implement Knowledge Read Endpoints

You will need to read the epic context from @.github/ISSUE/epic-architect-ai-tooling-as-mcp.md and the specific ticket details from @.github/ISSUE/ticket-implement-knowledge-read-endpoints.md before we begin.

tobiu added parent issue #7399 on Oct 7, 2025, 12:12 PM

tobiu added the enhancement label on Oct 7, 2025, 12:12 PM

tobiu added the help wanted label on Oct 7, 2025, 12:12 PM

tobiu added the good first issue label on Oct 7, 2025, 12:12 PM

tobiu added the hacktoberfest label on Oct 7, 2025, 12:12 PM

tobiu added the ai label on Oct 7, 2025, 12:12 PM

MannXo Oct 8, 2025, 2:12 PM

Hey @tobiu I can continue my contribution to #7399 by working on this issue. Let me know if you dont mind.

Cheers

tobiu Oct 8, 2025, 2:22 PM

Thx, appreciated!

tobiu assigned to @MannXo on Oct 8, 2025, 2:22 PM

MannXo Oct 8, 2025, 2:42 PM

Thx, appreciated!

I think I should wait for #7403 to complete before I can start this. I can take #7402 until then.

tobiu Oct 8, 2025, 2:46 PM

sounds good to me. hint: you need to add a comment to #7402, otherwise i can not assign it to you (github security policy).

tobiu Oct 24, 2025, 11:24 AM

i think this one was resolved via a 2 tickets in 1 PR. logic got converted to the new servers.