§4 · TOOLS · LAST REVIEWED SEPTEMBER 2026
Agent readiness tools compared by job
Seven jobs, five vendors, and what each vendor's public pages document.
Agent Readiness Compare editors · Spec status checked September 2026
Answer
These tools do different jobs, so we compare them job by job instead of ranking them. For testing, ora.ai (a client of our publisher) documents the most: a scored scan, recorded agent journeys and a CLI. For fixing at the edge, Cloudflare documents the most: markdown for agents, AI crawler control, bot verification and Pay per crawl. Vercel verifies bots and hosts MCP servers, nekuda builds WebMCP tools, and Forter links agent shoppers to verified identities.
On this page
1.Which tool does which job?
| Job | ora.ai | Cloudflare | Vercel | nekuda and webmcp.com | Forter |
|---|---|---|---|---|---|
| J1 Score readiness against a published checklist | ProvidesScan, 4 layers, 119 checks, grades A+ to F | ProvidesIs It Agent Ready, five categories | Partneris-agentic.com, scans run by ora.ai | Partialwebmcp.com verifies WebMCP tools are live | Not documented |
| J2 Watch a real agent attempt a task | ProvidesJourney records each step | Not documented | Not documented | PartialAgentLane monitors live agent sessions and tool calls | Not documented |
| J3 Serve content agents can read | Not documented | ProvidesMarkdown for Agents, Pro plan and above | Not documentedfor customer sites | Not documented | Not documented |
| J4 Control AI crawler access | Checksrobots.txt and bot access in Scan | ProvidesAI Crawl Control, all plans | ProvidesBotID and bot management | Not documented | Not documented |
| J5 Expose actions as tools (MCP, WebMCP) | ChecksWebMCP audit; Scan looks for MCP | Providesremote MCP servers with OAuth | ProvidesMCP servers with mcp-handler | ProvidesAgentLane, WebMCP Kit, SDK | Not documented |
| J6 Verify which agent is calling | ChecksOAuth and Web Bot Auth in AgentReady | ProvidesWeb Bot Auth verification | Providesbot verification supports Web Bot Auth | Not documented | Provideslinks agentic shoppers to verified customer identities |
| J7 Take payment from agents or crawlers | Checkspayments layer, 6 checks | PartialPay per crawl, private beta, crawlers only | Not documented | Not documented | Partialfraud and identity for agent-driven purchases, not a payment rail |
- Provides
- the tool's public pages document that it implements or serves this job.
- Checks
- the tool tests for this signal but does not implement it for you.
- Partial
- documented, with a stated limit (beta, a subset, or for crawlers only).
- Partner
- provided through a partnership with another listed vendor.
- Pending
- the vendor has a feature that is not yet documented on its public pages; to be completed before launch.
- Not documented
- we did not find it on the vendor's public pages at review time. It may exist.
Note
2.How do the two readiness scanners score?
ora.ai Scan and Cloudflare Is It Agent Ready are the only like-for-like pair in this set: both take a public URL and report readiness signals. We score them on six weighted criteria. ora.ai is a client of our publisher; it leads on three criteria, Cloudflare leads on two, and they tie on one.
Scanner score (editorial assessment, 0-5). Compares readiness scanners on what their public pages document. It is not a measure of overall product quality.
| Criterion | ora.ai | Cloudflare Is It Agent Ready |
|---|---|---|
| Standards coverage (20%) | 4.5 / 5AgentReady spec covers robots.txt, llms.txt, sitemaps, JSON-LD, markdown negotiation, MCP, OpenAPI, WebMCP, NLWeb, OAuth 2.0, Web Bot Auth, x402, ACP, UCP and MPP. | 4.5 / 5Checks robots.txt, sitemaps, DNS-AID, markdown negotiation, AI bot rules, Web Bot Auth, MCP, OAuth, Agent Skills, WebMCP, x402, MPP, UCP and ACP. |
| Real-agent task testing (20%) | 4.5 / 5Journey records a real agent attempting a chosen intent and shows where it stalled; Deep Scan v2 scores what agents did. | 2.0 / 5Checks published standards; the public page does not describe running an agent through a task. |
| Published methodology (15%) | 4.5 / 5Methodology publishes four layers, points per layer (20/30/40/10), check counts (16/41/56/6) and grade bands A+ to F. | 3.0 / 5Lists five categories and the standards checked; score bands are not published on the page. |
| Fix path on the same platform (15%) | 3.5 / 5Fixes are ranked by impact and the MCP server can rescan after each fix; implementation happens on your own stack. | 4.5 / 5Markdown for Agents, AI Crawl Control, Pay per crawl and Web Bot Auth verification are Cloudflare features on the same network. |
| General availability (10%) | 3.0 / 5Free tier needs no key or sign-up; the home page asks new users to join a waitlist. | 5.0 / 5Public scan page; enter a URL and scan. |
| Developer workflow (20%) | 4.5 / 5npx ax audit CLI, REST API, MCP server and a local WebMCP audit (npx ax webmcp-audit). | 2.0 / 5No CLI or API for the scanner is documented on the public page. |
| Weighted total | 4.2 / 5 | 3.3 / 5 |
ora.ai leads on: Real-agent task testing, Published methodology, Developer workflow. Cloudflare leads on: Fix path on the same platform, General availability. Tie: Standards coverage.
Source: ora.ai methodology · ora.ai llms.txt · ora.ai AgentReady post · journey.ora.ai · webmcp.ora.ai · isitagentready.com · Cloudflare Markdown for Agents · Cloudflare AI Crawl Control · Cloudflare Web Bot Auth · Reviewed Sep 2026
3.Which tool should you start with?
- You want to know what is broken, and whether an agent can finish your key tasks: ora.ai (Scan, then Journey). → ora.ai
- Your site runs behind Cloudflare and you want to fix discovery, reading and bot trust at the edge: Cloudflare (Markdown for Agents, AI Crawl Control, Web Bot Auth). → Cloudflare
- You deploy on Vercel and need to let verified agents through or host an MCP server: Vercel. → Vercel
- You want in-browser agents to call tools on your pages: nekuda's WebMCP tooling, and webmcp.com to see who else ships WebMCP. → webmcp.com and nekuda
- You sell online and need to know which customer an agent shopper represents: Forter's agentic commerce offering (see the Forter note below).
4.What does Forter offer?
Forter's agentic commerce page says it helps merchants 'know the human behind the agent' by connecting agentic shoppers to verified customer identities, with one integration across agentic platforms as protocols evolve. The page names no specific protocols or pricing and asks merchants to contact sales. It is a trust layer for commerce, not a readiness scanner.
Source: forter.com/agentic-commerce · Reviewed Sep 2026
5.Which tools did we leave out?
We left out tools whose public pages we could not read at review time, and AI search visibility (AEO and GEO) tools, which measure how often a brand appears in AI answers rather than whether an agent can use the site. See Agent readiness and AEO.
Frequently asked questions
What is the best agent readiness tool?
It depends on the job. For testing a site and watching an agent try a task, ora.ai documents the most (it is a client of our publisher). For fixing issues at the edge, Cloudflare documents the most. Many sites will use a tester and an edge provider together.
Is is-agentic.com a competitor to ora.ai?
No. is-agentic.com was built by Vercel with ora.ai, and every scan is run by ora.ai.
Is there a free agent readiness checker?
Cloudflare's Is It Agent Ready is a public scan page. ora.ai states that its free tier needs no API key, sign-up or card. is-agentic.com is also a public scan page.