What can you do with this server?

This server provides tools for auditing and analyzing websites' readiness for AI agents, including single URL audits, bulk audits, side-by-side comparisons, and leaderboard access. * Audit a single URL (audit_url): Checks a website's readiness, returning a level (0–5, from Hostile to Autonomous), a score percentage, and detailed check results. Free for 5 uses/day; unlimited on Pro. * Bulk audit (bulk_audit): Audits up to 50 URLs simultaneously, returning a summary table with level and score for each. Requires Pro authentication. * Compare URLs (compare_urls): Side-by-side comparison of 2-4 websites (up to 8 with Pro) for agent readiness, showing scores and detailed checks. * Leaderboard (get_leaderboard): Retrieves the public leaderboard of top agent-ready sites, with an optional limit (default 20, max 50). Free, no authentication required.

How do I use agentable-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agentable-mcp What's the agent readiness score for example.com?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

agentable-core

Python SDK and MCP server for seo4agent.com — agent-readiness auditing.

Install

pip install agentable-core

Related MCP server: coven-mcp

MCP Server (Claude Desktop / Cursor / Windsurf)

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "agentable": {
      "command": "agentable-mcp",
      "env": {
        "AGENTABLE_TOKEN": "your_jwt_token"
      }
    }
  }
}

Get your token at seo4agent.com → Settings.

Available MCP tools

Tool	Description	Plan
`audit_url`	Audit a single URL for agent readiness	Free (5/day) · Pro (unlimited)
`bulk_audit`	Audit up to 50 URLs in parallel	Pro only
`compare_urls`	Compare URLs side by side (2 Free / up to 8 Pro)	Free + Pro
`get_leaderboard`	Public leaderboard of top agent-ready sites	Free

Python SDK

import asyncio
from agentable import AgentableClient

async def main():
    client = AgentableClient(token="your_token")
    
    # Single audit
    result = await client.audit("https://example.com")
    print(f"Level {result['level']} — {result['score_pct']}%")
    
    # Bulk audit
    results = await client.bulk_audit([
        "https://site1.com",
        "https://site2.com",
    ])
    
    # Compare
    comparison = await client.compare([
        "https://openai.com",
        "https://anthropic.com",
    ])

asyncio.run(main())

x402 — Pay per audit (no account required)

The REST endpoint supports the x402 payment protocol — pay $0.10 USDC per audit directly from any EVM wallet on Base, no account needed.

import { wrapFetchWithPayment } from "@x402/fetch";
import { CdpX402Client } from "@coinbase/cdp-sdk/x402";

const client = new CdpX402Client();
const fetchWithPayment = wrapFetchWithPayment(fetch, client);

const res = await fetchWithPayment("https://seo4agent.com/audit/run", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ url: "https://example.com" }),
});

See the x402 buyer quickstart for full setup.

Environment variables

Variable	Default	Description
`AGENTABLE_TOKEN`	—	JWT token from seo4agent.com
`AGENTABLE_BASE_URL`	`https://seo4agent.com`	API base URL

Available Tools

4 tools

audit_urlA

Audit a website for AI/agent readiness. Returns a readiness level (0-5), score percentage, and individual check results. Level 5 = Autonomous (fully agent-ready), Level 0 = Hostile. Free plan: 5 audits/day. Pro: unlimited.

Inputs: url (required).

bulk_auditA

Audit multiple websites at once (up to 50). Returns a summary table with level and score for each URL. Requires Pro subscription.

Inputs: urls (required).

compare_urlsA

Compare websites side by side for agent readiness. Free plan: up to 2 URLs. Pro plan: up to 8 URLs. Returns scores and check results for each URL.

Inputs: urls (required).

get_leaderboardA

Get the public leaderboard of top agent-ready websites. No authentication required.

Inputs: limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored 2026-09-09 17:55 across 4 tools

Disambiguation5/5

Each tool targets a clearly distinct workflow: single URL audit, bulk audit, side-by-side comparison, and leaderboard access. Even though bulk_audit and compare_urls both handle multiple URLs, their descriptions differentiate summary output from comparative analysis.

Naming Consistency4/5

Most tools follow a verb_noun pattern: audit_url, compare_urls, get_leaderboard. bulk_audit is a minor deviation since it reads as an adjective-noun phrase rather than an action-object pair, but the overall style remains coherent and readable.

Tool Count5/5

Four tools is well-scoped for this niche server. Each tool covers a distinct user need without unnecessary redundancy, and the count matches the apparent purpose of auditing and comparing agent readiness.

Completeness4/5

The core audit lifecycle is covered: single, bulk, comparison, and public leaderboard operations. Minor gaps exist, such as no historical audit retrieval or detailed report export, but agents can complete primary workflows without dead ends.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

agentreadyA
app.vercel.agentready-rho
Scan any website or MCP server for agent readiness: 0-100 score, a fix per failing check. Free.
Agent Orchestration Browser Automation Testing & QA Tools
111
https://agentready-rho.vercel.app/api/mcp
Pylon SEOB
io.pylonseo
Audit, rank-track and analyze SEO for sites via an authenticated MCP server.
Marketing Search
311
https://api.pylonseo.io/mcp
anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2
https://api.anotherai.dev/mcp
mcp
com.screenshotink
Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.
Browser Automation Web Scraping
2
https://mcp.screenshotink.com/mcp

Related MCP Servers

Lighthouse MCP
Web Scraping App Automation Monitoring
danielsogl
A
license
B
quality
B
maintenance
MCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for performance, accessibility, SEO, and security analysis.
Updated a day ago (2026-11-09 21:40 UTC)
11
1,975 npm
75
MIT
coven-mcpofficial
Agent Orchestration Browser Automation AI & Machine Learning
covenai-dev
A
license
Not graded
quality
D
maintenance
MCP server for website auditing and AI visibility measurement using the COVEN v2.0.1 methodology, offering tools to scan, score, and optimize sites for agent traffic.
Updated 6 months ago (2026-04-28 13:36 UTC)
MIT
aeo-mcp
Web Scraping Marketing
arthurcarlsonn
A
license
A
quality
C
maintenance
An MCP server that gives AI agents tools to inspect a website's visibility to AI answer engines, including crawler permissions, llms.txt, structured data, on-page signals, and a full 29-check AI-readiness audit.
Updated 4 months ago (2026-07-05 02:00 UTC)
5
55 npm
MIT
@gridwork/siteaudit
Browser Automation Testing & QA Tools
thegridwork
A
license
A
quality
D
maintenance
An MCP server that audits websites for accessibility (WCAG 2.1 AA/EAA), performance, SEO, design quality, and mobile responsiveness, providing actionable scores, grades, and prioritized fixes.
Updated 7 months ago (2026-04-08 13:56 UTC)
6
MIT