NEXUS AGI
link.eblas.nexusv1.0.0Updated Oct 3, 2026
Keeps AI agents from repeating costly mistakes: past decisions, rules and incidents, shared by all.
Overview
AI-generated overview
A remote MCP endpoint that lets an assistant consult a shared store of past decisions, rules, and incidents so agents avoid repeating costly mistakes.
- What it does
- NEXUS AGI is a remote MCP server reached over streamable HTTP at a fixed endpoint. According to its registry description, it keeps AI agents from repeating costly mistakes by holding past decisions, rules, and incidents that are shared by all. No tools are listed in the manifest, so the exact operations an assistant can call are not documented here.
- When to use it
- Consider it when several agents or sessions should draw on the same record of earlier decisions, rules, and incidents instead of re-deriving them. It is aimed at teams that want continuity across agents rather than a single isolated assistant.
- Requirements
- A remote MCP client that supports streamable HTTP, plus network access to the provider's endpoint. The manifest declares no authentication, no environment variables, and no headers, and no local package or runtime is needed.
Before you install
The manifest declares no authentication, so anything sent to this endpoint may not be access-controlled; avoid submitting secrets or sensitive material. The description says past decisions, rules, and incidents are shared by all, which suggests content may be visible to other users or agents. No tools are listed, so what it can read or change cannot be verified before connecting.
Installation
In SourceWeft
- Open NEXUS AGI in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"nexus-agi": {
"type": "http",
"url": "https://nexus.eblas.link/mcp"
}
}
}Tools
0Tool metadata has not been indexed yet.
Version history
1- v1.0.0LatestOct 3, 2026
