Agent View
The site as an AI agent gets it, beside the site as a person sees it. What it can read, what it has to cut away, and what it never sees.
Skip to content
PricingSolutionsEssentialsPlusEnterpriseFeaturesLiterature ManagementLiterature Monitoring
Discover, read, organize, and cite research literature, all in one platform.
Manage your research, or ask a question, and get answers drawn from 165M+ publications and 182M+ patents.
Every citation sourced, linked, verifiable.
Try for free
Explore options
Image: readcube-app-hero-half
Tools for every stage of your literature review
The rest of the page is in full screen.
[Skip to content](https://about.readcube.com/#fl-main-content) [](https://about.readcube.com/) # Discover, read, organize, and cite research literature, **all in one platform.** Manage your research, or ask a question, and get answers drawn from 165M+ publications and 182M+ patents. Every citation sourced, linked, verifiable. [Try for free](https://about.readcube.com/30-day-trial/) [Explore options](https://about.readcube.com/pricing/)  ## Tools for every stage of your literature review - - - - ### Hundreds of companies, from startups to global leaders, trust ReadCube’s award-winning platform to transform how they work with scholarly literature. ## Transform your research workflow  ### Discover Search 160M+ pubs and patents, or set up alerts.  ### Organize Build a shared library. Tag and annotate every file.  ### Understand Ask a question, get an answer linked to its source.  ### Cite Insert citations into word or google docs.  ### Review PRISMA, dual review, and AI screening. ## Find a plan that works for you ### Essential For individual researchers building their library. Organize, read, and cite your papers — with AI to help you get through them faster. [Learn More](https://about.readcube.com/solution/essentials/) ### Plus For power users and small research groups. More shared libraries, more AI, and more room to grow as your work does. [Learn More](https://about.readcube.com/solution/plus/) ### Enterprise For organizations running research at scale. Everything in Team, plus optional AI-powered literature review, unlimited scale, and dedicated support. [Learn More](https://about.readcube.com/solution/enterprise/) ### "We deployed ReadCube almost 5 years ago to help our teams work with scientific literature more effectively, and it continues to play an essential role in our day-to-day research." Damir Kasper Associate Director of IT @ C4 Therapeutics #### ReadCube A Digital Science solution Your centralized, smart reference library solution to dramatically improve the way you discover, organize, read, annotate, share, and cite your research.  #### Use Cases #### Features #### Resources #### Support #### **Digital Science** Research. Smarter. Innovative, AI-powered technology driving global research progress – solutions for researchers, institutions, governments, funders, and publishers. [www.digital-science.com](https://www.digital-science.com/) #### Discover the Digital Science Ecosystem © 2026 Digital Science & Research Solutions Inc. All rights reserved. [Scroll To Top](https://about.readcube.com/#)
No <main>: Wrap the page’s own content in <main>, so a reader knows where it starts and stops, and Clean can be measured.
The figures
2 pages, set against the 167,893 sites with figures.
- Readablehigher is better
- 100%2 of 2 pages
- All 167,893 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- Nonemiddle page
- All 167,893 sitesNo place yetWith no figure, it has no place.
Of the words before script, the share that are the page and not menus, footer and forms. 2 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 5,734tokens
- About 2,867 a page
To read every page once. A long page that answers well is not worse for it. Tokens are estimated at about 4 characters each.
How its pages spread on Clean
0 pages measured. Not measured: 2 with no <main> or no words.
Against its rivals
The sites nearest it by what they do, with figures. Close means similar work, not better.
| Readinghigher is better | Costnot scored | ||
|---|---|---|---|
| Site | Readable | Clean | Tokens a page |
| readcube.comThis site, 2 pages | 100% | None | 2,867 |
| electricdata.solutions7 pages | 100% | 96% | 1,006 |
| saascubes.com100 pages | 100% | 94% | 1,657 |
| protocols.io100 pages | 24% | 75% | 456 |
First of 4 on Readable.
AI crawler access
What robots.txt says to each, as read on October 23, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Not named | Training models | Falls to User-agent: * |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | Falls to User-agent: * |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | Falls to User-agent: * |
| ClaudeBotAnthropic | Not named | Training models | Falls to User-agent: * |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Not named | Training Gemini | Falls to User-agent: * |
| bingbotMicrosoft | Not named | Bing and Copilot | Falls to User-agent: * |
Every AI crawler mttr checks may read it. Not named means the rules for every crawler apply.
Every page
Worst first. Each opens in Agent View at the top.
2 pages of 2 lose something. Pick a loss to see what to do about it.Open the action plan
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| / | 309 | No <main> | Yes | Yes | 862 | No <main> |
| /privacy | 2,955 | No <main> | Yes | Yes | 4,872 | No <main> |
Show where it stands
A card, a badge and a line, each with the figures.
A badge for the site
<a href="https://mttr.si/agent-view/readcube.com"><img src="https://mttr.si/agent-view/readcube.com/badge.svg" alt="Agent View: 100% readable" height="20"></a>
The figures in one line
readcube.com in Agent View: 100% of pages readable, better than 47% of sites; Clean not measured; 5,734 tokens to read all 2 pages. mttr.si/agent-view/readcube.com
What to do next
Fix the pages, let an agent do it, and read the site again to see the figures move.
Fix what agents miss
- Wrap 2 pages in <main>Clean measured
Connect your agent
Claude Code, Codex or Cursor reads the site’s fixes over MCP, fixes a page in your code, has mttr read it again, and checks the fix landed.
https://mttr.si/mcpSet up an agent
Claim the site
Prove it is yours with a DNS record or a file. Your agent can then reach its reads and jobs, and set each change to wait for your approval.
Claim the siteDrawn from the HTML mttr fetched on its read of October 23, 2026, not a screenshot, and only from the 2 pages read, where the read stopped at its page limit. An assistant’s own reader may differ. Tokens are estimated at about 4 characters each. A site an agent reads well is not a site an assistant cites.