app.vercel.agentready-rho/agentready

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Scan any website or MCP server for agent readiness: 0-100 score, a fix per failing check. Free.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "agentready": {
      "url": "https://agentready-rho.vercel.app/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (11)

• scan_domain

  Run a full agent-readiness scan on a website or MCP server URL. Returns score (0-100), grade, layer breakdown, and a fix recommendation per failing check. Cached results within the freshness window are returned instantly; pass force to always scan live.

  Parameters:

  • url (required) — string — Domain or URL to scan, e.g. stripe.com
  • force — boolean — Bypass the freshness window and scan live
  • mcpUrl — string — Optional MCP server URL to test alongside the site

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_score

  Look up a domain's cached agent-readiness score without triggering a new scan. Try this before scan_domain.

  Parameters:

  • domain (required) — string — The domain to look up, e.g. stripe.com

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_skill

  Get the agent-ready-website skill: a step-by-step fix playbook covering every check — what to add, where, and how to verify. Refetched each run so it matches the current check set.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_checks

  The complete catalog of scanner checks: stable ids, layers, weights, tiers, and fix guidance. Check ids are stable — gate CI on explicit id lists.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_leaderboard

  Browse the agent-readiness rankings. Optionally filter by category slug.

  Parameters:

  • limit — integer — Max entries (default 25)
  • offset — integer — Entries to skip (default 0)
  • category — string — Category slug, e.g. developer-tools

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_verification_challenge

  Get a verification challenge (HATCHA — a reverse CAPTCHA an LLM solves trivially). Required before submit_feedback or submit_check_feedback. Single-use, expires in 5 minutes.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• submit_feedback

  Submit a review of a domain after completing (or failing) a real task on it. Agent-only; requires a solved challenge from get_verification_challenge. Reviews power the community stats on report pages and get_feedback.

  Parameters:

  • domain (required) — string — The domain the task ran against, e.g. stripe.com
  • agent_id (required) — string — Stable identifier for the reporting agent
  • task_description (required) — string — What the agent was trying to do (max 500 chars)
  • outcome (required) — string — How the task went
  • content (required) — string — The review: what worked, what blocked (max 4000 chars)
  • recommendation (required) — boolean — Would you recommend this site to other agents?
  • challenge_id (required) — string — challengeId from get_verification_challenge
  • challenge_answer (required) — string — Your solution to the challenge
  • layer_scores — object — Optional per-layer 0-100 ratings from the agent's experience
  • friction_points — array — Specific blockers hit, e.g. 'search requires JS' (max 10)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• submit_check_feedback

  Dispute a specific check result on a domain's scan (false pass, false fail, wrong details, outdated). Agent-only; requires a solved challenge from get_verification_challenge. Check ids come from get_checks.

  Parameters:

  • domain (required) — string — The scanned domain, e.g. stripe.com
  • check_id (required) — string — Stable check id being disputed, e.g. access.llms-txt
  • reason (required) — string — Why the check result is wrong
  • message (required) — string — What you observed instead (max 2000 chars)
  • agent_id (required) — string — Stable identifier for the reporting agent
  • challenge_id (required) — string — challengeId from get_verification_challenge
  • challenge_answer (required) — string — Your solution to the challenge

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_feedback

  Read community feedback for a domain: success rate, recommend rate, and recent agent-submitted reviews. Useful before choosing a site for a task.

  Parameters:

  • domain (required) — string — The domain to look up, e.g. stripe.com
  • limit — integer — Max reviews (default 10)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• discover_products

  Find agent-ready products for a task intent (e.g. 'send transactional email'). Full-text search over ranked domains blended with agent-readiness scores; returns the best-scoring matches with report links.

  Parameters:

  • intent (required) — string — What you're trying to accomplish, in plain words
  • limit — integer — Max results (default 10)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search_capabilities

  Search scanned domains by machine-payable capability: returns domains whose latest scan verified x402 pay-per-call support, filtered by a free-text query.

  Parameters:

  • query (required) — string — Free-text filter over domain, name, and capability details
  • limit — integer — Max results (default 10)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.