scanned May 7, 2026

Scope

tryscope.app

ai-mlVisit site →

Scope is a platform that helps make products discoverable and usable by AI agents

16/100

Tier 1 · Agent-Unreadable

Content answers8/100
Protocol plumbing50/1008 of 16 checks pass
Re-audit2990h 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

0 of 15 come back answered. 2 get a hedge. 13 meet silence.

0 answerable2 half-answers13 silent

Goes silent · getting-started · high importance

For a product with ~50 API endpoints, how long should I realistically budget for a full Scope implementation — days or weeks?

Goes silent · integration · high importance

We use LangChain for our internal agents — does Scope have a native integration or do I need to build a custom wrapper around your API?

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

Sign in to claim

The fix queue

84 points sit between tryscope.app and 100: 15 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.

01getting-started · importance highGoes silent+7 content pts est.

For a product with ~50 API endpoints, how long should I realistically budget for a full Scope implementation — days or weeks?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated getting-started or implementation guide page that includes time estimates for onboarding based on product complexity (e.g., API endpoint count). Add this to the FAQ section.

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

02integration · importance highGoes silent+7 content pts est.

We use LangChain for our internal agents — does Scope have a native integration or do I need to build a custom wrapper around your API?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated Integrations or Developers page that lists supported frameworks (LangChain, LlamaIndex, etc.) and explains whether native integrations exist or if customers need to use a REST API.

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

03pricing · importance highGoes silent+7 content pts est.

I'm trying to compare plans — what's the exact monthly API call limit on your free tier before I hit a hard stop versus just throttling?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated pricing page with clear plan tiers including specific API call limits, throttling vs hard stop behavior, and comparison table. Ensure this page is linked from main navigation and retrievable by search.

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

04technical · importance highGoes silent+7 content pts est.

Your homepage mentions making products 'discoverable by AI agents' — what specific protocol or standard does Scope use? Is it MCP, something custom, or just structured metadata?

What the pages say

No page on the site addresses this.

The fix

Add technical documentation explaining whether Scope implements MCP (Model Context Protocol), uses structured metadata/schemas, or relies on another standard for agent discoverability. Buyers evaluating technical architecture need this specificity.

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

05limits · importance mediumGoes silent+7 content pts est.

If my product's documentation is massive, how does Scope handle context window limits? Does it chunk intelligently or do I need to pre-process?

What the pages say

No page on the site addresses this.

The fix

Create technical documentation or a FAQ section explaining how Scope handles large documentation sets — specifically whether it uses intelligent chunking, what preprocessing (if any) is required from users, and how it manages context window limits when processing extensive product documentation.

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

06migration · importance mediumGoes silent+7 content pts est.

We're currently using Stytch's agent toolkit — can Scope import our existing agent configurations or do we start from scratch?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated migration or integrations page that addresses importing configurations from popular agent platforms like Stytch, including whether automated import is supported or if users must reconfigure manually.

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

07operations · importance mediumGoes silent+7 content pts est.

If I update my API schema, does Scope automatically detect changes or do I need to manually re-submit? And how much notice for breaking changes on your end?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated API documentation or developer portal page covering schema management, change detection workflows, and breaking change policies with specific notice periods.

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

08security · importance mediumGoes silent+7 content pts est.

We're SOC 2 prep — how long does Scope retain the actual content of API calls versus just metadata logs?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated Security or Trust Center page that documents data retention policies, SOC 2 compliance status, and specifically addresses how long API call content is retained versus metadata/logs. This is critical information for SOC 2 preparation that buyers need to evaluate vendors.

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

09support · importance mediumGoes silent+7 content pts est.

What's the actual SLA for technical support response on the Team plan — is it business hours only or 24/7 with a guaranteed time?

What the pages say

No page on the site addresses this.

The fix

Create a dedicated pricing page that clearly lists plan tiers (including 'Team') with specific support SLAs, response time guarantees, and availability hours (business hours vs. 24/7).

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

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

For real-time agent coordination, do you support webhooks with delivery guarantees or just polling? What's the retry policy on failed deliveries?

What the pages say

No page on the site addresses this.

The fix

Add a developer documentation section or API reference page covering integration patterns, including webhook support, delivery guarantees, and retry policies for real-time agent coordination.

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

11limits · importance lowGoes silent+7 content pts est.

Is there a limit on concurrent agent sessions per user or is it purely rate-limited by total API calls?

What the pages say

No page on the site addresses this.

The fix

Add a documentation page, pricing page, or technical FAQ that specifies usage limits, rate limits, and any concurrency restrictions for agent sessions.

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

12operations · importance lowGoes silent+7 content pts est.

Can I maintain separate Scope configurations for staging and production, or is it one environment per account with manual switching?

What the pages say

No page on the site addresses this.

The fix

Create documentation or FAQ content explaining whether Scope supports multiple environments per account, how staging/production configurations work, and any environment switching mechanisms.

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

13technical · importance lowGoes silent+7 content pts est.

Can I define custom tool schemas that don't map 1:1 to my REST endpoints, or is Scope strictly an API-to-tool converter?

What the pages say

No page on the site addresses this.

The fix

Add technical documentation or a developer/docs section explaining how Scope integrates with APIs, whether it supports custom tool schema definitions, and how flexible the API-to-tool mapping is.

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

Hedged · 2 of 15 questions

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

14Can I see which specific AI agent platforms (Claude, GPT-4, Gemini, etc.) are actually hitting my product's Scope endpoints, or is that aggregated?analyticsCollapsed+3 pts est.

Can I see which specific AI agent platforms (Claude, GPT-4, Gemini, etc.) are actually hitting my product's Scope endpoints, or is that aggregated?

What the pages say

The chunks mention that Scope captures analytics including "tool calls, errors, friction, latency, and the agent's reasoning behind each decision" [1][3][9], and that they "point real browsing and coding agents at your product, the way a customer's agent would" [17]. However, there is no specific information about whether analytics are broken down by specific AI agent platform (Claude, GPT-4, Gemini, etc.) versus aggregated. The FAQ section lists "Which AI agents do you support?" as a question [16], but the answer content is not present in the retrieved chunks.

The fix

The FAQ section at https://tryscope.app/ contains a question 'Which AI agents do you support?' but the answer body was not retrieved—likely a JS-collapsed accordion or dynamic content that the crawler failed to expand. Expanding this section would answer the buyer's question about platform-specific visibility.

Where we looked: tryscope.app, tryscope.app, /blog/scope-memo, tryscope.app

confidence low · grounding synthesized · weight 0.55 · Collapsed

15Does Scope track whether agent interactions actually convert to successful user outcomes, or just that the agent 'used' the tool?analyticsHedges+2 pts est.

Does Scope track whether agent interactions actually convert to successful user outcomes, or just that the agent 'used' the tool?

What the pages say

Scope tracks whether agents successfully complete tasks and achieve value, not merely whether they 'used' the tool. The platform simulates how AI agents 'discover, understand, and complete tasks with your product, across the workflows your users actually attempt' [1][4][5], and specifically watches 'where they stall, which docs they misread, and which tool calls fail' and 'why agents quietly close the tab and move on to other tasks' [14]. However, the chunks do not explicitly clarify whether Scope correlates these agent interactions to downstream human user conversions or business outcomes (e.g., did the agent's successful task completion lead to a paying customer). The focus is on agent task completion and 'conversion' in the sense of the agent not abandoning the product [7][8][13], not necessarily tracking through to end-user business results.

The fix

Add explicit clarification on whether Scope's analytics connect agent interaction success to downstream human user conversion events (e.g., signup, purchase, retention) or if it remains at the agent task-completion layer.

Where we looked: tryscope.app, tryscope.app, /blog/scope-memo, tryscope.app

confidence medium · grounding synthesized · weight 0.65 · Vague

Protocol plumbing · 50/1008 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 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+6 pts est.

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

Standardllmstxt.orgCommunity spec

Content signalAccess+6 pts est.
Install snippet
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

StandardCloudflare proposalVendor proposal

Clean crawlAccess+6 pts est.

StandardSitedex metricSitedex metric

MCP cardInteraction+6 pts est.

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

StandardModel Context ProtocolCommunity spec

OpenAPI specInteraction+6 pts est.

StandardOpenAPI SpecIndustry standard

WebMCP widgetInteraction+6 pts est.

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

StandardW3C WebMCP draftW3C / WHATWG

Organization schemaIdentity+6 pts est.

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

StandardSchema.org + JSON-LDIndustry standard

Sitemap lastmodDiscoverability+6 pts est.

Standardsitemaps.orgIndustry standard

Already passing 8 of 16: robots.txt, sitemap.xml, AI crawler access, Markdown negotiation, Server-rendered content, Canonical URLs, Meta descriptions, HTML lang attribute.

Ask this site’s index

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

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

Claude Code

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

One command, then the agent has it.

Cursor / Continue

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