Skip to content

Machine Relations Index

by machinerelations.ai · remote · no sign-in to list tools · v1.0.0 · published by ai.machinerelations

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

Read only
CompareRegistry entry

4 tools: 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http mri https://machinerelations.ai/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Only reads 4Claude Code: allow
  • mri_get_categoryReturn one category's question shapes (best tools, how buyers choose, comparisons, top lists, problem-first research, is it worth it, news) and the evidence state of each: publishe…No findings

    Why it is in this group

    • The name "mri_get_category" says "get": a word for reading.
    Description, as the server wrote it
    Return one category's question shapes (best tools, how buyers choose, comparisons, top lists, problem-first research, is it worth it, news) and the evidence state of each: published with rates, collecting, or not collectable.

    Annotations the server declares

    • title: Get an MRI category
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • mri_get_cited_sourcesRanked source domains that AI answer engines cite for one category and question shape, with citation rate (share of monitored answer runs citing the domain), rank, percentile and s…No findings

    Why it is in this group

    • The name "mri_get_cited_sources" says "get": a word for reading.
    Description, as the server wrote it
    Ranked source domains that AI answer engines cite for one category and question shape, with citation rate (share of monitored answer runs citing the domain), rank, percentile and source role (editorial publication, vendor-owned, analyst research, community, academic/government, market database, wire distribution). Use to answer 'which publications/sources does ChatGPT or Perplexity cite for <category>' or 'where should a <category> brand earn coverage to be cited by AI'.

    Annotations the server declares

    • title: Which sources AI engines cite
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • mri_get_domainFor one domain or URL, return how often AI answer engines cite it: overall citation rate, which engines cite it, confidence tier, rank among all cited domains and within its source…No findings

    Why it is in this group

    • The name "mri_get_domain" says "get": a word for reading.
    Description, as the server wrote it
    For one domain or URL, return how often AI answer engines cite it: overall citation rate, which engines cite it, confidence tier, rank among all cited domains and within its source role, and per-category segment rates. Use to answer 'does ChatGPT/Perplexity cite <site>' or 'how authoritative is <publication> as an AI source'.

    Annotations the server declares

    • title: How often AI engines cite a site
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • mri_list_categoriesList every Machine Relations Index category (e.g.No findings

    Why it is in this group

    • The name "mri_list_categories" says "list": a word for reading.
    Description, as the server wrote it
    List every Machine Relations Index category (e.g. cybersecurity, fintech, enterprise-software, ai-visibility-geo) with the question shapes that have published citation rates, plus the source-role vocabulary. Call this first to get a valid category key.

    Annotations the server declares

    • title: List MRI categories
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http mri https://machinerelations.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__mri__mri_list_categories",
      "mcp__mri__mri_get_category",
      "mcp__mri__mri_get_cited_sources",
      "mcp__mri__mri_get_domain"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as mri. Review it before you use it.