scanned Jun 2, 2026

Namedesk

namedesk.app

ai-mlVisit site →

Namedesk provides AI-era due diligence for names, analyzing how AI reads and recognizes them

82/100

Tier 5 · Agent-Native

Content answers77/100
Protocol plumbing94/10015 of 16 checks pass
Re-audit2382h ago· 1 credit

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

7 of 15 come back answered. 7 get a hedge. 1 meets silence.

7 answerable7 half-answers1 silent

Goes silent · technical · low importance

Do AI visibility scores vary by geographic region or LLM localization settings? I need to know if my .com performs differently in US vs EU search contexts.

The fix queue

18 points sit between namedesk.app and 100: 8 open questions and 1 missing protocol check, ordered by estimated payoff.

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

01technical · importance lowGoes silent+7 content pts est.

Do AI visibility scores vary by geographic region or LLM localization settings? I need to know if my .com performs differently in US vs EU search contexts.

What the pages say

No page on the site addresses this.

The fix

Add a FAQ or documentation page explaining whether AI visibility scores vary by geographic region or LLM localization settings (e.g., US vs EU model versions).

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

Hedged · 7 of 15 questions

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

02I'm bootstrapping and want to test Namedesk before committing — how many domain lookups do I get on the free plan per month, and do unused lookups roll over?pricingHedges+2 pts est.

I'm bootstrapping and want to test Namedesk before committing — how many domain lookups do I get on the free plan per month, and do unused lookups roll over?

What the pages say

Namedesk does not appear to offer a monthly free plan. New accounts receive 10 free credits on signup—enough for one full research read, one coining run, or one round of alternatives. After that, you pay as you go for credit packs. The site does not specify whether unused free credits roll over or expire, though paid credit packs are described as having "no expiry."

The fix

Clarify on the pricing page or FAQ whether the 10 free signup credits expire or roll over, and explicitly confirm there is no recurring monthly free tier.

Where we looked: /llms.txt, /faqs, namedesk.app

confidence medium · grounding synthesized · weight 0.65 · Vague

03Your homepage mentions 'LLMs doing the searching' — which specific models do you test against? GPT-4, Claude, Gemini, or others? Is the list expanding?technicalHedges+2 pts est.

Your homepage mentions 'LLMs doing the searching' — which specific models do you test against? GPT-4, Claude, Gemini, or others? Is the list expanding?

What the pages say

Namedesk tests against eight specific models: Claude, GPT-5, Gemini, Kimi, Llama, Mistral, Qwen, and gpt-oss. These are described as four frontier models (Claude, GPT-5, Gemini, Kimi) and four open baselines (Llama, Mistral, Qwen, gpt-oss). The chunks do not mention GPT-4 specifically, and they do not state whether the list is expanding.

The fix

Add a statement on the homepage or in FAQs about whether the list of tested LLMs is static or planned to expand.

Where we looked: namedesk.app, namedesk.app, namedesk.app

confidence high · grounding synthesized · weight 0.70 · Vague

04How exactly is the 'AI visibility score' calculated? Is it based on citation frequency, semantic relevance, or something else — and what's the 0-100 scale based on?technicalHedges+2 pts est.

How exactly is the 'AI visibility score' calculated? Is it based on citation frequency, semantic relevance, or something else — and what's the 0-100 scale based on?

What the pages say

The retrieved chunks do not explain exactly how the AI Visibility Score is calculated or what the 0-100 scale is based on. Chunks [1] and [3] list the score as metadata returned by the get_info tool. Chunk [18] shows a sample report where notion.so has a median score of 86/100 across 8 models, with individual model scores ranging from 65/100 to 95/100, plus an 'AI mindshare' count of mentions across topics. No chunk specifies whether the score derives from citation frequency, semantic relevance, model recall rates, or a composite formula.

The fix

Add a methodology page or FAQ entry that defines the AI Visibility Score formula and what the 0-100 scale represents (e.g., median model recognition, semantic relevance percentile, or citation frequency).

Where we looked: /.well-known/mcp.json, /.well-known/webmcp.json, /research/notion.so

confidence high · grounding synthesized · weight 0.70 · Vague

05We're building a bulk research tool — what's the API rate limit per second or minute, and is there burst capacity for batch jobs?limitsHedges+2 pts est.

We're building a bulk research tool — what's the API rate limit per second or minute, and is there burst capacity for batch jobs?

What the pages say

Namedesk's v1 API has no per-second or per-minute rate limits beyond the credit gate. Read endpoints (status polls, pricing reads, wallet) are uncapped, and the credit balance is the only throttle with no separate API quotas. Batch jobs are limited to 100 domains per submission. The documentation does not mention burst capacity.

The fix

Explicitly state whether batch jobs support burst capacity, or clarify that the absence of rate limits means no bursting mechanism is needed.

Where we looked: /docs/api, /docs/api, /faqs

confidence medium · grounding synthesized · weight 0.65 · Vague

06What export formats do you support for research reports? PDF, CSV, JSON — and can I white-label exports for client presentations?operationsHedges+2 pts est.

What export formats do you support for research reports? PDF, CSV, JSON — and can I white-label exports for client presentations?

What the pages say

Namedesk supports Markdown (one-click download in the dashboard), JSON (via the API), and CSV (bulk pricing results and via the API pricing endpoint with `?format=csv`). The retrieved chunks do not mention PDF export. White-labeled or co-branded reports for client presentations are not currently offered.

Source: /faqs, /openapi.json

confidence high · grounding synthesized · weight 0.70 · Vague

07Can I supply my own custom prompts to test how my domain performs for specific industry queries, or am I limited to your standard test set?llm-integrationHedges+2 pts est.

Can I supply my own custom prompts to test how my domain performs for specific industry queries, or am I limited to your standard test set?

What the pages say

Namedesk's research relies on a structured prompt such as "What industry is this startup in?" to generate AI-era signals, but none of the retrieved chunks describe a way for users to supply their own custom prompts or test sets. The API endpoints for submitting research jobs and rerunning appraisals only document mode (full/quick) and quick-read flags, with no prompt-override parameter.

The fix

Add explicit documentation to the API reference or FAQs clarifying whether users can supply custom prompts, or confirm that evaluations rely on a fixed standard prompt set.

Where we looked: /insights/ai-confidently-wrong, /docs/api, /openapi.json

confidence medium · grounding synthesized · weight 0.65 · Vague

08If I delete my account, how long do you retain my domain research history — and is it purged from your LLM testing logs as well?securityHedges+2 pts est.

If I delete my account, how long do you retain my domain research history — and is it purged from your LLM testing logs as well?

What the pages say

Namedesk's privacy policy states that personal information—which includes 'the domains you research' and 'the activity history of your account'—is retained 'for as long as your account is active and for a reasonable period thereafter to satisfy our legal, tax, and accounting obligations or to resolve disputes.' It does not specify exactly how long that 'reasonable period' lasts. The retrieved chunks do not address whether your domain research history is purged from LLM testing logs. The FAQ notes that when Namedesk sends a domain to an external model provider for analysis, it sends only the domain string and that 'your identity, email, and account details never leave Namedesk,' but this does not speak to internal LLM testing logs.

The fix

Specify the exact retention period (e.g., 30 or 90 days) for domain research history after account deletion in the privacy policy, and add a clear statement about whether internal LLM testing logs are purged or de-identified.

Where we looked: /privacy, /privacy, /faqs

confidence medium · grounding synthesized · weight 0.65 · Vague

What the pages already answer cleanly

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

pricingAnswered

We're a domain portfolio company doing 50,000+ lookups monthly — is there published volume pricing or do I need to contact sales for a custom tier?

What the pages say

Namedesk does not publish volume pricing tiers. The site states that day-to-day pricing is pay-as-you-go via standard credit packs, with no tier gate unlocking additional features at any scale. If you are running names at real volume — such as a large portfolio, an agency workflow, or heavy API traffic — you must email hello@namedesk.app to arrange custom or enterprise pricing.

Source: /faqs

confidence high · grounding stated · weight 1.00 · Answered

operationsAnswered

If I research the same domain weekly, how often does your LLM search data refresh? Daily, weekly, or real-time?

What the pages say

Namedesk does not refresh LLM search data on a fixed daily, weekly, or real-time schedule. Reports—including LLM-derived signals (`ai_signals`)—are cached and served immediately without consuming a credit. They refresh only when Namedesk ships a meaningfully better version of the underlying analysis (the next read then refreshes the report and consumes a credit), or when you force a fresh appraisal via the API using `POST /v1/domains/{domain}/rerun`.

Source: /faqs, /openapi.json, /openapi.json

confidence high · grounding synthesized · weight 0.95 · Answered

integrationAnswered

Can I get notified via webhook when a domain's AI visibility score changes significantly, or do I need to poll the API manually?

What the pages say

Namedesk does not offer webhooks. The API documentation and changelog describe a poll-only workflow: you submit research jobs and poll `GET /v1/research-jobs/:id` for status and `GET /v1/research-jobs/:id/report` for results. The v1 API is described as having eight REST endpoints with no webhook, event subscription, or push notification mechanism mentioned.

Source: /docs/api, /docs/api, /changelog

confidence high · grounding synthesized · weight 0.95 · Answered

brand-analysisAnswered

Beyond AI visibility, does Namedesk flag if my domain name has unintended associations or toxic connotations in LLM training data?

What the pages say

Yes. Namedesk can flag negative or off-putting associations because its read comes from frontier AI models rather than a fixed word list: if a name sounds like something unfortunate, leans on a controversial meaning, or sits too close to an association you wouldn't want next to your company, that tends to surface in the AI and brand signals, and the verdict takes it into account.

Source: /faqs

confidence high · grounding stated · weight 1.00 · Answered

technicalAnswered

Does Namedesk let me compare my domain's AI visibility directly against 3-5 competitors in one report, or is it only single-domain analysis?

What the pages say

Namedesk is single-domain analysis. While you can submit bulk jobs of up to 100 domains, the DomainReport schema is explicitly a 'Comprehensive research report for a single domain,' and multi-domain jobs return collections of individual per-domain reports rather than one unified competitive comparison. There is no evidence of a side-by-side AI visibility benchmark across 3–5 competitors in a single report.

Source: /openapi.json, /docs/api, /docs/api, /docs/api, /faqs

confidence high · grounding synthesized · weight 0.95 · Answered

technicalAnswered

For historical research data queries, what's the max results per page and does pagination use cursor-based or offset-based navigation?

What the pages say

The maximum results per page is 100 (values above 100 are clamped to 100), and pagination uses cursor-based navigation—you pass `?cursor=…` from a previous response to fetch the next page, and the response includes a `next_cursor` field.

Source: /openapi.json, /docs/api

confidence high · grounding stated · weight 1.00 · Answered

supportAnswered

What's the guaranteed response time for technical support on paid plans — and is there a dedicated channel for API outage escalations?

What the pages say

Namedesk does not offer guaranteed response times for technical support, and there is no dedicated channel for API outage escalations. The site explicitly states there are "no SLAs, no guaranteed response times, and no priority-support tiers," and the only support channel listed is hello@namedesk.app, which reaches the team within a business day, usually sooner.

Source: /faqs, /faqs

confidence high · grounding stated · weight 1.00 · Answered

Protocol plumbing · 94/10015 of 16 checks pass · each fix +6 protocol pts est.

The other half of the score: 16 checks for the files and headers agents look for. The 1 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.

Markdown negotiationRendering+6 pts est.

StandardRFC 9110 + 7763IETF RFC

Already passing 15 of 16: robots.txt, sitemap.xml, llms.txt, AI crawler access, Content signal, Clean crawl, Server-rendered content, MCP card, OpenAPI spec, WebMCP widget, Canonical URLs, Meta descriptions, HTML lang attribute, Organization schema, Sitemap lastmod.

Ask this site’s index

Sitedex already serves namedesk.app as an MCP endpoint. Ask namedesk.app 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/namedesk-app/mcp

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

Claude Code

claude mcp add namedesk --transport http https://mcp.sitedex.dev/s/namedesk-app/mcp

One command, then the agent has it.

Cursor / Continue

{
  "mcpServers": {
    "namedesk": {
      "url": "https://mcp.sitedex.dev/s/namedesk-app/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": "namedesk.app",
  "tools": [
    { "name": "search", "description": "Search namedesk.app's indexed content." },
    { "name": "get_page", "description": "Fetch a page from namedesk.app 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