Machine Relations Index

ai.machinerelationsv1.0.0Updated Oct 2, 2026

Which source domains AI answer engines cite, by buyer category and question shape.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

A remote MCP endpoint that reports which source domains AI answer engines cite, broken down by buyer category and question shape.

What it does
Machine Relations Index is a hosted, streamable-HTTP MCP server. According to its registry description, it surfaces which source domains AI answer engines cite, organized by buyer category and question shape. No tool list is published, so the exact operations an assistant can call are not documented in the supplied material.
When to use it
Consider it when you want an assistant to look up citation patterns for AI answer engines, for example to see which domains tend to be cited for a given buyer category or type of question. It is a research and reference source rather than a tool for editing your own content.
Requirements
A remote MCP client that supports streamable HTTP, connecting to the provider's endpoint. No authentication, environment variables, or headers are declared, and no local package or runtime is needed.
Before you install
The server is third-party and hosted remotely, so queries and any context you send go to the provider. No credentials are requested, but the published material lists no tools, so verify what data is transmitted and returned before relying on it. Treat citation data as informational, not authoritative.

Installation

In SourceWeft

  1. Open Machine Relations Index in the dashboard and add it to a workspace.
  2. 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": {
    "mri": {
      "type": "http",
      "url": "https://machinerelations.ai/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 2, 2026