Skip to content

io.github.msanchezgrice/agentready

by msanchezgrice · remote · no sign-in to list tools · v1.0.0 · published by GitHub user msanchezgrice

Scan any public site for AI-agent visibility; get scored findings, a machine-readable fix pack, and

Changes · 3
CompareRegistry entry

7 tools: 3 change things and 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 agentready https://www.agentready.me/api/mcp

Tools

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

7 tools

Changes things 3Claude Code: ask
  • audit_openapi_readinessStatically inspect an OpenAPI 3.0 or 3.1 JSON object or JSON string for operation identity, auth and scopes, errors, examples, retries, limits, lifecycle, pagination, and workflows…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Statically inspect an OpenAPI 3.0 or 3.1 JSON object or JSON string for operation identity, auth and scopes, errors, examples, retries, limits, lifecycle, pagination, and workflows. No API operation is executed.
  • scan_urlRun an AgentReady scan of a public URL.No findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Run an AgentReady scan of a public URL. Returns the 0-100 score, per-phase findings, top priorities, and the Fix Pack v2 implementation contract. Repository paths remain candidate targets until a connected-repository resolver proves them.
  • verify_fixesRe-scan a public URL and evaluate fix-specific stable ids from a previous v1 or v2 Fix Pack.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Re-scan a public URL and evaluate fix-specific stable ids from a previous v1 or v2 Fix Pack. A fix closes when its finding id is absent; score delta is secondary evidence only.
Only reads 4Claude Code: allow
  • check_crawler_accessFetch robots.txt and a bounded public page through validated redirects, then inspect named-token path rules, final delivery, X-Robots-Tag, and HTML meta robots.No findings

    Why it is in this group

    • The description's first verb is "fetch": a word for reading.
    Description, as the server wrote it
    Fetch robots.txt and a bounded public page through validated redirects, then inspect named-token path rules, final delivery, X-Robots-Tag, and HTML meta robots. Named-bot edge/WAF treatment remains unobservable.
  • get_fix_packScan a public URL and return Fix Pack v2: prioritized fixes with stable ids, observed evidence, candidate target URLs and repository paths, review gates, and fix-specific acceptanc…No findings

    Why it is in this group

    • The name "get_fix_pack" says "get": a word for reading.
    Description, as the server wrote it
    Scan a public URL and return Fix Pack v2: prioritized fixes with stable ids, observed evidence, candidate target URLs and repository paths, review gates, and fix-specific acceptance assertions for a coding agent.
  • get_public_reportRead the latest saved public scan report or bounded history using its opaque report id.No findings

    Why it is in this group

    • The name "get_public_report" says "get": a word for reading.
    Description, as the server wrote it
    Read the latest saved public scan report or bounded history using its opaque report id. Reports are only created after explicit opt-in and expire after 30 days.
  • validate_a2a_agent_cardStatically validate an A2A Agent Card JSON object.No findings

    Why it is in this group

    • The name "validate_a2a_agent_card" says "validate": a word for reading.
    Description, as the server wrote it
    Statically validate an A2A Agent Card JSON object. Strict-current evidence and legacy interoperability are reported separately; no agent endpoint or skill is invoked.

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 agentready https://www.agentready.me/api/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__agentready__get_fix_pack",
      "mcp__agentready__get_public_report",
      "mcp__agentready__check_crawler_access",
      "mcp__agentready__validate_a2a_agent_card"
    ],
    "ask": [
      "mcp__agentready__scan_url",
      "mcp__agentready__verify_fixes",
      "mcp__agentready__audit_openapi_readiness"
    ],
    "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 agentready. Review it before you use it.