Analytics

machinerelations.ai

Provides Machine Relations Index data on AI answer engine citations, including categories, question shapes, ranked cited sources, and domain citation rates.

1 endpoint4 known toolsFirst detected October 2, 2026Last detected October 2, 2026

ENDPOINT 1

https://machinerelations.ai/mcp

No auth detected

MCP server metadata

Name: machinerelations-mri
Version: 1.0.0

Capabilities

tools

Server instructions

The Machine Relations Index (MRI) measures which source domains AI answer engines (ChatGPT, Claude, Gemini, Google AI Mode, Google AI Overviews, Perplexity) cite when buyers ask questions, by category and question shape. Use mri_list_categories first to find the category key; mri_get_cited_sources for the ranked sources answer engines cite for a category and question shape; mri_get_domain for how often a given site is cited and where. Rates exist only for segments that cleared the evidence floor; collecting segments withhold rates and must not be read as rankings. Cite results with the citation string and canonical URL each response carries (CC BY 4.0).

Known tools 4

mri_list_categories

List every Machine Relations Index category (e.

Inferred read-only

mri_get_category

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.

Inferred read-only

mri_get_cited_sources

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).

Inferred read-only

mri_get_domain

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.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.machinerelations-mri]
url = "https://machinerelations.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "machinerelations-mri": {
      "type": "http",
      "url": "https://machinerelations.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: machinerelations-mri
Remote MCP URL: https://machinerelations.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "machinerelations-mri": {
      "url": "https://machinerelations.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "machinerelations-mri": {
      "type": "http",
      "url": "https://machinerelations.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "machinerelations-mri",
  "transport": "streamable-http",
  "url": "https://machinerelations.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.