Claude MarketplacesSubmit
mlava avatar

Agent Ready

mlava/agent-ready-mcp

Wraps the Agent Ready hosted API to audit any URL against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol manifests like MCP server cards and agents.json. Exposes three tools: scan_site to run fresh scans with 60 checks across four spec families, get_scan to retrieve results by ID, and ask for natural-language queries over the methodology corpus. Ships with three built-in prompts that chain tools together for end-to-end workflows from URL to remediation plan. Requires an Agent Ready Pro API key. The stdio wrapper polls the hosted REST API with configurable timeouts, so large scans may return a running placeholder you fetch later. Useful when you need structured, actionable readability feedback for agentic sites.

GitHub stars
2
tools
3
auth
Secret needed
transport
STDIO, HTTP
env var
1
last updated
Sep 7, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://agent-ready.dev/api/v1/mcp --name agent-ready-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http agent-ready-mcp https://agent-ready.dev/api/v1/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 3 tools

Verified live against the running server on Nov 6, 2026.

scan_siteRuns the agent-ready.dev scanner against a URL and returns structured results: Vercel score, llmstxt.org score, and per-check findings with remediation hints. Scans may take up to ~60s; for larger scans the tool returns a scan id and asks you to poll with get_scan.2 params

Runs the agent-ready.dev scanner against a URL and returns structured results: Vercel score, llmstxt.org score, and per-check findings with remediation hints. Scans may take up to ~60s; for larger scans the tool returns a scan id and asks you to poll with get_scan.

Parameters* required
pageLimitinteger
Maximum number of pages to crawl. Defaults to your tier's per-scan page limit when omitted.
url*string
Full URL of the site to scan, e.g. https://example.com. Must be a public http(s) address.
get_scanFetches a completed or in-progress scan by its id. Only scans owned by the authenticated API key's user are returned.1 params

Fetches a completed or in-progress scan by its id. Only scans owned by the authenticated API key's user are returned.

Parameters* required
id*string
The scan id returned by scan_site (also the share token in a /scan/<id> URL).
askNatural-language search (NLWeb /ask) over Agent Ready's own content — scoring methodology, the check registry, the specs it validates, and the content library (explainers, comparisons, how-to guides, glossary). Returns Schema.org-typed result objects. Optional itemType narrows...3 params

Natural-language search (NLWeb /ask) over Agent Ready's own content — scoring methodology, the check registry, the specs it validates, and the content library (explainers, comparisons, how-to guides, glossary). Returns Schema.org-typed result objects. Optional itemType narrows...

Parameters* required
itemTypestring
Restrict results to a content type: methodology, checks, specs, llms-txt, check, page (explainers/guides/glossary), or any (default: all types).one of methodology · checks · specs · llms-txt · check · page
modestring
"list" (default) returns matching items; "summarize" returns a synthesized answer.one of list · summarize
q*string
Natural-language question to search Agent Ready's docs, scoring methodology, check registry, and content library (explainers, comparisons, how-to guides, glossary).

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

AGENT_READY_API_KEYsecret

Agent Ready Pro API key for scan_site and get_scan. ask and validate_structured_data work without one. Issue a key at https://agent-ready.dev/dashboard/api-keys.

Readme

agent-ready-mcp

MCP server for Agent Ready — scan any URL for AI agent readability against the Vercel Agent Readability Spec, the llmstxt.org standard, and agent-protocol manifests (MCP server cards, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb). 72 checks across four spec families — 40 site and page checks (15 site-wide + 25 per-page), 10 against llmstxt.org, and 22 against agent-protocol manifests — each with per-check fix guidance, plus a separate accessibility sub-score from 23 WCAG 2.2 / layout-stability checks.

Hosted at https://agent-ready.dev/api/v1/mcp (Streamable HTTP); this package is a thin stdio wrapper around the same REST endpoints, distributed via npm for local MCP clients (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf).

Features

View the full README on GitHub

Details

Repository
github.com/mlava/agent-ready-mcp
Website
agent-ready.dev
Categories
AI & LLM Tools, Cloud & Infrastructure
Package
agent-ready-mcp
Transport
STDIO, HTTP
Auth
Required
Registry
MCP registry, active
Resources
5
Prompts
3
Tools verified
Nov 6, 2026

More from mlava

Related AI & LLM Tools MCP servers

View all
1rumblingb avatarAgent Audit Mcprumblingb/agent-audit-mcpImmutable audit trail for agent-to-agent interactions2stars
2base76-research-lab avatarCognos Session Memorybase76-research-lab/cognos-session-memoryCognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.1stars
3dingdawg-dev avatarDingdawg Finance Agentdingdawg-dev/dingdawg-finance-agentFinancial analysis AI. Forecasting, audit prep, SOX/GAAP compliance. Accuracy compounds with use.1stars
4dingdawg-dev avatarDingdawg Healthcare Agentdingdawg-dev/dingdawg-healthcare-agentHIPAA-aware healthcare AI. Clinical documentation, compliance checks, audit prep. Free local tier.1stars
5cognitivemyriad avatarVerified Repo Memorycognitivemyriad/mcp-verified-repo-memoryStale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).1stars
6dingdawg avatarDingdawg Legal Agentdingdawg/dingdawg-agent-1AI contract review, clause drafting, compliance checklists & legal research.0stars