AI & Machine Learning

agentfriendlyrank.com

Evaluates and reports on website readiness for AI agents, providing scores, rankings, and comparisons.

1 endpoint5 known toolsFirst detected September 7, 2026Last detected September 7, 2026

ENDPOINT 1

https://agentfriendlyrank.com/mcp

No auth detected

MCP server metadata

Name: agentfriendlyrank
Version: 1.0.0

Capabilities

tools

Server instructions

AgentFriendlyRank measures what AI agents can and cannot do on a website, scored 0–100 against a published rubric (v1.0.1). These tools are read-only. To get a site scanned, a human submits https://agentfriendlyrank.com/scan (works without JavaScript); the resulting /scan/{id} URL can then be polled with get_scan_status. Full REST equivalent with OpenAPI: https://agentfriendlyrank.com/api/v1/openapi.json. Documentation: https://agentfriendlyrank.com/docs.

Known tools 5

get_site_report

The latest published Agent Readiness Report for a domain: score out of 100, grade, pillar scores, the fixes ranked first, and all 27 checks with captured evidence.

Inferred read-only

get_leaderboard

Published sites ranked by Agent Readiness Score, highest first, optionally filtered by category (ecommerce, saas, content, other).

Inferred read-only

compare_sites

Two published sites side by side: both summaries and every check with each side's status and points.

Inferred read-only

get_scan_status

Status of a scan by id (from the /scan/{id} URL a human receives after submitting the scan form).

Inferred read-only

get_rubric

The published Agent Readiness rubric (v1.0.1): four pillars, 27 checks, point weights, grade bands and changelog.

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.agentfriendlyrank]
url = "https://agentfriendlyrank.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentfriendlyrank": {
      "type": "http",
      "url": "https://agentfriendlyrank.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentfriendlyrank
Remote MCP URL: https://agentfriendlyrank.com/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": {
    "agentfriendlyrank": {
      "url": "https://agentfriendlyrank.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentfriendlyrank": {
      "type": "http",
      "url": "https://agentfriendlyrank.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentfriendlyrank",
  "transport": "streamable-http",
  "url": "https://agentfriendlyrank.com/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.