scanned Jun 3, 2026

ROBOTS.AI

ROBOTS.AI is a directory for discovering and learning about various robots from different manufacturers.

31/100

Tier 2 · Basic Presence

Content answers24/100

Protocol plumbing47/1007 of 15 checks pass

Scored by asking 15 questions a buyer of a ai-ml product asks, then grading this site’s own pages: answered, hedged (partial or vague), or silent (no page answers it). How scoring works

15 buyer questions · graded against the site’s own pages

1 of 15 come back answered. 4 get a hedge. 10 meet silence.

1 answerable4 half-answers10 silent

Goes silent · pricing · high importance

We're a robot manufacturer planning to list on your marketplace — what's your exact commission percentage on sales, and does it vary by robot category or volume tier?

Goes silent · operations · medium importance

For robots connected through your platform, how long is operational telemetry data retained, and can manufacturers export historical data if they stop using your marketplace?

This report is public. Own robots.ai? Claiming is free: crawl every page, re-audit as you fix, and track your score over time.

The fix queue

69 points sit between robots.ai and 100: 14 open questions and 8 missing protocol checks, ordered by estimated payoff.

Point estimates are per fix under scoring v2. They are not additive to a promised total.

01pricing · importance highGoes silent+7 content pts est.

We're a robot manufacturer planning to list on your marketplace — what's your exact commission percentage on sales, and does it vary by robot category or volume tier?

What the pages say

No page on the site addresses this.

The fix

Create a 'For Manufacturers' or 'Sell on Robots.ai' page that discloses the exact commission percentage on sales and whether it varies by robot category or volume tier.

Where we looked: /.well-known/webmcp.json, robots.ai

confidence high · grounding synthesized · weight 0.00 · Absent

02operations · importance mediumGoes silent+7 content pts est.

For robots connected through your platform, how long is operational telemetry data retained, and can manufacturers export historical data if they stop using your marketplace?

What the pages say

robots.ai does not state how long operational telemetry data is retained, nor does it mention whether manufacturers can export historical data. The retrieved content presents robots.ai as a robotics directory and marketplace focused on search, pricing, and listings, with no discussion of operational data connectivity or retention policies.

The fix

Add a data governance, privacy, or operations page covering telemetry retention, historical data export, and offboarding policies for manufacturers.

Where we looked: robots.ai, /.well-known/agentroot.json, /.well-known/webmcp.json

confidence high · grounding synthesized · weight 0.00 · Absent

03integration · importance mediumGoes silent+7 content pts est.

You mention supporting various robot types — do you provide native ROS 2 integration packages, or is middleware bridging left to the manufacturer? Specifically, do you support ROS 2 Humble or only Iron/Jazzy?

What the pages say

No page on the site addresses this.

The fix

Add a developer integrations page or FAQ specifying ROS 2 support, including whether native packages are provided or middleware bridging is left to manufacturers, and list supported distributions (e.g., Humble, Iron, Jazzy).

Where we looked: robots.ai, /.well-known/agentroot.json

confidence high · grounding synthesized · weight 0.00 · Absent

04security · importance mediumGoes silent+7 content pts est.

Your site mentions 'enterprise security' — which specific certifications do you hold (ISO 27001, SOC 2 Type II, etc.) and are these scoped to just the marketplace or also the robot control infrastructure?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated security/compliance page that lists specific certifications held (e.g., ISO 27001, SOC 2 Type II) and explicitly defines their scope (marketplace vs. robot control infrastructure).

confidence high · grounding world-knowledge · weight 0.00 · Absent

05security · importance lowGoes silent+7 content pts est.

For dual-use robots with potential ITAR or EAR restrictions, does your platform handle export control screening automatically, or is compliance verification entirely the manufacturer's responsibility?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated compliance or legal page that addresses whether robots.ai performs ITAR/EAR export control screening or if that responsibility falls entirely on manufacturers.

Where we looked: robots.ai, /llms.txt

confidence high · grounding synthesized · weight 0.00 · Absent

06technical · importance lowGoes silent+7 content pts est.

If internet connectivity drops, do robots lose all platform functionality or is there a local edge cache for critical commands? What's the maximum offline duration before mandatory re-authentication?

What the pages say

No page on the site addresses this.

The fix

Publish technical architecture or operations documentation addressing edge caching, offline command behavior, and authentication timeouts if robots.ai plans to offer robot fleet management; otherwise, clarify site scope as a directory marketplace.

Where we looked: /.well-known/agentroot.json, /.well-known/webmcp.json, robots.ai

confidence high · grounding synthesized · weight 0.00 · Absent

07technical · importance lowGoes silent+7 content pts est.

Your llms.txt file — how frequently is it regenerated, and does it include real-time robot availability or only static capability descriptions? What's the cache TTL for AI agents consuming it?

What the pages say

No page on the site addresses this.

The fix

Add a specification section to llms.txt or a linked 'For AI Agents' page that documents generation cadence, cache TTL, and whether availability data is real-time or static.

confidence high · grounding world-knowledge · weight 0.00 · Absent

08migration · importance lowGoes silent+7 content pts est.

We're migrating from Robotic Markup Language (RML) catalogs on competitor platforms — does your import tool preserve custom manufacturer metadata fields, or do we need to remap to your schema?

What the pages say

The retrieved chunks from robots.ai do not contain any information about RML catalog imports, import tools, custom manufacturer metadata fields, or schema remapping.

The fix

Add a migration or data-import documentation page that addresses RML compatibility, custom metadata field mapping, and whether remapping is required.

Where we looked: /.well-known/agentroot.json, robots.ai, /.well-known/webmcp.json

confidence high · grounding synthesized · weight 0.00 · Absent

09pricing · importance lowGoes silent+7 content pts est.

Do you support Robot-as-a-Service (RaaS) subscription billing through your platform, and if so, what payment terms can manufacturers set — monthly, usage-based per hour, or outcome-based pricing?

What the pages say

No page on the site addresses this.

The fix

Add a dedicated page or FAQ section that states whether robots.ai provides RaaS subscription billing infrastructure for manufacturers and details the supported payment terms (e.g., monthly, usage-based per hour, outcome-based).

Where we looked: /.well-known/agentroot.json, /.well-known/webmcp.json, /.well-known/webmcp.json, /.well-known/webmcp.json, /.well-known/webmcp.json

confidence high · grounding synthesized · weight 0.00 · Absent

10support · importance lowGoes silent+7 content pts est.

For critical robot control failures during live operations, what's your escalation path and guaranteed response time? Is 24/7 phone support available or only ticket-based with business-hours SLAs?

What the pages say

No page on the site addresses this.

The fix

Publish a dedicated Support or Contact page outlining escalation paths for critical robot control failures, guaranteed response times, and available support channels (e.g., 24/7 phone vs. ticket-based business-hours SLAs).

confidence high · grounding world-knowledge · weight 0.00 · Absent

Hedged · 4 of 15 questions

A buyer gets something, then has to guess the rest. Expand any row for the evidence and the fix.

11Your agentroot.json mentions AI agent discovery — which version of the AgentRoot protocol are you implementing, and do you support the 2024-06 schema extensions for capability negotiation?technicalHedges+2 pts est.

Your agentroot.json mentions AI agent discovery — which version of the AgentRoot protocol are you implementing, and do you support the 2024-06 schema extensions for capability negotiation?

What the pages say

robots.ai implements AgentRoot version ar1, as shown by the DNS TXT record `_agentroot.robots.ai TXT "v=ar1 zone=https://robots.ai/.well-known/agentroot.json"`. None of the retrieved chunks mention support for the 2024-06 schema extensions for capability negotiation.

The fix

Add a protocol version field and explicit schema extension support documentation (e.g., 2024-06 capability negotiation) to the agentroot.json file or a dedicated AgentRoot protocol specification page.

Where we looked: robots.ai, /.well-known/agentroot.json

confidence medium · grounding synthesized · weight 0.65 · Vague

12I see you have a webmcp.json file — what specific MCP (Model Context Protocol) endpoints do you expose for robot control, and do you support streaming telemetry or just request-response?technicalHedges+2 pts est.

I see you have a webmcp.json file — what specific MCP (Model Context Protocol) endpoints do you expose for robot control, and do you support streaming telemetry or just request-response?

What the pages say

The chunks do not describe MCP endpoints for physical robot control. According to the AgentRoot zone file, robots.ai exposes one MCP endpoint at `https://robots.ai/api/mcp` with transport `sse` (Server-Sent Events). The documented tools are `search_robots`, `compare_prices`, `check_availability`, and `get_specs` — these provide product search, pricing, and specification data for commercial robots, not robot control. Streaming telemetry from robots is not mentioned.

Source: /.well-known/agentroot.json, /.well-known/webmcp.json, /.well-known/webmcp.json

confidence high · grounding synthesized · weight 0.70 · Vague

13What are the API rate limits for directory searches versus robot control commands, and do these differ between free developer accounts and paid manufacturer tiers?limitsPage missing+2 pts est.

What are the API rate limits for directory searches versus robot control commands, and do these differ between free developer accounts and paid manufacturer tiers?

What the pages say

robots.ai lists directory and search API endpoints (e.g., robots.ai/api/search and robots.ai/api/directory) and tools such as search_robots, compare_prices, check_availability, and get_specs, but the retrieved chunks do not specify rate limits for any endpoints, do not mention robot control command APIs, and do not document free developer accounts or paid manufacturer tiers.

The fix

Add a dedicated API documentation or pricing page that lists rate limits for each endpoint, clarifies whether robot control commands are offered, and distinguishes limits between free developer and paid manufacturer account tiers.

Where we looked: /.well-known/webmcp.json, /.well-known/agentroot.json, robots.ai, /llms.txt

confidence high · grounding synthesized · weight 0.70 · Page missing

14How many robots are currently listed in your directory, and how many of those have live availability for immediate purchase versus just informational listings?operationsHedges+2 pts est.

How many robots are currently listed in your directory, and how many of those have live availability for immediate purchase versus just informational listings?

What the pages say

The retrieved chunks do not state the total number of robots listed in the directory, nor do they provide a numeric breakdown of how many robots have live availability for immediate purchase versus informational-only listings. The site describes a "Curated catalog of commercial humanoids, quadrupeds, and industrial systems shipping today and on the near horizon" (chunks [11]–[13]), and lists at least one robot — Tesla Optimus Gen 3 — as "Now Shipping" with a starting price of $19,999 (chunk [20]). Multiple chunks also reference API endpoints and tools for checking real-time availability and purchase options (chunks [1]–[2]), indicating the directory tracks availability status, but no aggregate counts or ratios are disclosed.

The fix

Publish total directory statistics and a breakdown by availability status (e.g., 'In stock / Ships now' vs 'Pre-order' vs 'Informational') on the directory landing page or a dedicated 'About our data' page.

Where we looked: /.well-known/agentroot.json, /.well-known/webmcp.json, /.well-known/webmcp.json, robots.ai, /llms.txt, /.well-known/webmcp.json

confidence medium · grounding synthesized · weight 0.65 · Vague

What the pages already answer cleanly

1 of 15. Answered with enough specificity for a buyer to act on. This is the bar the queue above is chasing.

technicalAnswered

Can a single AI agent registered on your platform control multiple robots simultaneously, or is the 1:1 agent-to-robot mapping enforced? If multi-robot is possible, what's the upper limit?

What the pages say

Robots.ai does not support robot control capabilities. The platform is described as an agent-native robotics directory, offering only informational tools and skills such as robot search, price comparison, availability checks, spec lookup, and industry analysis. Because the platform provides data discovery rather than actuation or command interfaces, there is no agent-to-robot control mapping and no multi-robot control limit.

Source: /.well-known/agentroot.json, robots.ai

confidence high · grounding synthesized · weight 0.95 · Answered

Protocol plumbing · 47/1007 of 15 checks pass · each fix +7 protocol pts est.

The other half of the score: 15 checks for the files and headers agents look for. The 8 below are installs, not judgment calls, and most are an afternoon. Expand any for the snippet and the standard it follows. They sit after the queue because none of them changes what your pages say.

llms.txtDiscoverability+7 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

Standardllmstxt.orgCommunity spec

Content signalAccess+7 pts est.

Install snippet

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

StandardCloudflare proposalVendor proposal

Markdown negotiationRendering+7 pts est.

StandardRFC 9110 + 7763IETF RFC

MCP cardInteraction+7 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

StandardModel Context ProtocolCommunity spec

OpenAPI specInteraction+7 pts est.

StandardOpenAPI SpecIndustry standard

WebMCP widgetInteraction+7 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

StandardW3C WebMCP draftW3C / WHATWG

Canonical URLsHygiene+7 pts est.

Install snippet

<link rel="canonical" href="https://robots.ai/" />

StandardRFC 6596IETF RFC

Organization schemaIdentity+7 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

StandardSchema.org + JSON-LDIndustry standard

Already passing 7 of 15: robots.txt, sitemap.xml, AI crawler access, Clean crawl, Server-rendered content, Meta descriptions, HTML lang attribute.

Ask this site’s index

Sitedex already serves robots.ai as an MCP endpoint. Ask robots.ai anything an AI agent might ask, and see what its index returns. (To score your own site, use the form below.)

Snippets & configs

For developers and the engineer-on-call: copy these into your tools or your site.

Files from this audit

Built from this crawl. Download or copy each, then install it at the path noted.

llms.txt

Built from this crawl. Install at /llms.txt so agents start here.

organization.json

Organization JSON-LD, pre-filled from this crawl. Wrap in a ld+json script.

server-card.json

MCP server card built from this crawl. Host at /.well-known/mcp/server-card.json.

webmcp.json

WebMCP discovery manifest built from this crawl. Host at /.well-known/webmcp.json.

MCP endpoint

https://mcp.sitedex.dev/s/robots-ai/mcp

The URL anyone's agent points at. Read-only; safe to share.

Claude Code

claude mcp add robots --transport http https://mcp.sitedex.dev/s/robots-ai/mcp

One command, then the agent has it.

Cursor / Continue

{
  "mcpServers": {
    "robots": {
      "url": "https://mcp.sitedex.dev/s/robots-ai/mcp"
    }
  }
}

Drop into mcp.json.

WebMCP: two parts

WebMCP-capable browsers run the widget at runtime. Crawlers without JS rendering need the discovery manifest to find your tool surface. Install both.

1 · Widget script

<script async src="https://sitedex.dev/widget.js"></script>

Drop in <head>. WebMCP-capable browsers (Chrome 146+ Origin Trial) call navigator.modelContext.provideContext() via this script.

2 · Discovery manifest

{
  "$schema": "https://wellknownmcp.org/schemas/webmcp.json",
  "name": "robots.ai",
  "tools": [
    { "name": "search", "description": "Search robots.ai's indexed content." },
    { "name": "get_page", "description": "Fetch a page from robots.ai as markdown." }
  ]
}

Host alongside the script at /.well-known/webmcp.json. Crawlers that don't render JS rely on this.

Your turn

See which of these questions your site goes silent on.

Free, about 5 minutes. We crawl your site, test it against the buyer questions your category asks, and name what’s vague, contradictory, or missing, plus the files AI agents look for.

ComingEmbeddable grade badgeScore history and deltasOpt-in public board