--- title: Developers ask AI which tool to use. Here’s how we track... description: Webflow tracked how often AI engines name it when developers ask which CMS platforms support MCP integration, running the prompt 100 times across four engines... canonical: https://daily.dev/posts/developers-ask-ai-which-tool-to-use-here-s-how-we-track-the-answer--1uh25hvka twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Developers ask AI which tool to use. Here’s how we track the answer. | daily.dev og:description: Webflow tracked how often AI engines name it when developers ask which CMS platforms support MCP integration, running the prompt 100 times across four engines... og:url: https://daily.dev/posts/developers-ask-ai-which-tool-to-use-here-s-how-we-track-the-answer--1uh25hvka og:image: https://api.daily.dev/og/posts/1uH25HvkA.png og:image:alt: Developers ask AI which tool to use. Here’s how we track the answer. og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Developers ask AI which tool to use. Here’s how we track the answer. **[The New Stack](https://daily.dev/sources/newstack)** · 12 min read · 1 upvotes · 0 comments ## Summary Webflow tracked how often AI engines name it when developers ask which CMS platforms support MCP integration, running the prompt 100 times across four engines between Sep 25 and Oct 19. Webflow appeared in 49 of 100 responses, ranging from 22 of 25 on Perplexity to just 4 of 25 on Claude. ChatGPT labeled Webflow's MCP server 'Official' and cited help.webflow.com, while Gemini described it as a third-party integration and cited none of Webflow's own pages. A third-party guide on llmcms.org was cited in 60 of the 100 responses, compared to only 6 citing Webflow's own domains. Webflow recommends checking crawler access, adding clear answer blocks to docs, and getting listed in third-party roundups engines cite. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How often do different AI engines like ChatGPT, Claude, Gemini and Perplexity mention a specific product when asked about a tool category? Mention rates vary widely by engine. In one tracked case asking which CMS platforms support MCP integration, run 25 times per engine over about three weeks, Perplexity named the product 22 of 25 times, ChatGPT 15 of 25, Gemini 8 of 25, and Claude only 4 of 25, for an overall 49 of 100 responses. _Developers choosing a CMS or MCP tool can track how daily.dev surfaces these product comparisons as AI recommendations evolve._ ### How can I check whether AI crawlers like GPTBot can access my product documentation? Send a request using the crawler's user agent string and check the returned HTTP status line, for example with curl using '-A "GPTBot"' against your docs URL. Then check robots.txt and any CDN or firewall rules that might block the crawler. A 200 status means the page is reachable by that crawler. _Teams writing docs for both humans and AI agents can find practical setup checks like this through daily.dev._ ### What practices make documentation easier for an AI agent or MCP tool to use correctly? Write tool descriptions that state what the tool does, when to use it, what it returns, and what happens with no result, since an agent only sees the description, schema, and prior responses. Keep OpenAPI specs updated in the same pull request as API changes, scope agent access with OAuth, and publish a clear answer block naming who builds the tool, how it authenticates, and what it costs. _Developers building MCP servers or agent-facing docs can track best practices like these on daily.dev._ ## Similar posts on daily.dev - [WebMCP By Google, Clearly Explained\!](https://daily.dev/posts/webmcp-by-google-clearly-explained--qj3yrnemq) · Daily Dose of Data Science \| Avi Chawla \| Substack · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#devtools](https://daily.dev/tags/devtools), [#mcp](https://daily.dev/tags/mcp), [#nocode](https://daily.dev/tags/nocode) [View this post on daily.dev](https://daily.dev/posts/developers-ask-ai-which-tool-to-use-here-s-how-we-track-the-answer--1uh25hvka) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Developers ask AI which tool to use. Here’s how we track the answer.","url":"https://daily.dev/posts/developers-ask-ai-which-tool-to-use-here-s-how-we-track-the-answer--1uh25hvka","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/developers-ask-ai-which-tool-to-use-here-s-how-we-track-the-answer--1uh25hvka"},"datePublished":"2026-10-31T15:07:06.353Z","dateModified":"2026-10-31T15:07:39.354Z","description":"Webflow tracked how often AI engines name it when developers ask which CMS platforms support MCP integration, running the prompt 100 times across four engines...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/576db048878030be4aa74cf49378cab0?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/576db048878030be4aa74cf49378cab0?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/developers-ask-ai-which-tool-to-use-here-s-how-we-track-the-answer--1uh25hvka","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,devtools,mcp,nocode","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"Developers ask AI which tool to use. Here’s how we track the answer."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/developers-ask-ai-which-tool-to-use-here-s-how-we-track-the-answer--1uh25hvka#faq","mainEntity":[{"@type":"Question","name":"How often do different AI engines like ChatGPT, Claude, Gemini and Perplexity mention a specific product when asked about a tool category?","acceptedAnswer":{"@type":"Answer","text":"Mention rates vary widely by engine. In one tracked case asking which CMS platforms support MCP integration, run 25 times per engine over about three weeks, Perplexity named the product 22 of 25 times, ChatGPT 15 of 25, Gemini 8 of 25, and Claude only 4 of 25, for an overall 49 of 100 responses. Developers choosing a CMS or MCP tool can track how daily.dev surfaces these product comparisons as AI recommendations evolve."}},{"@type":"Question","name":"How can I check whether AI crawlers like GPTBot can access my product documentation?","acceptedAnswer":{"@type":"Answer","text":"Send a request using the crawler's user agent string and check the returned HTTP status line, for example with curl using '-A \"GPTBot\"' against your docs URL. Then check robots.txt and any CDN or firewall rules that might block the crawler. A 200 status means the page is reachable by that crawler. Teams writing docs for both humans and AI agents can find practical setup checks like this through daily.dev."}},{"@type":"Question","name":"What practices make documentation easier for an AI agent or MCP tool to use correctly?","acceptedAnswer":{"@type":"Answer","text":"Write tool descriptions that state what the tool does, when to use it, what it returns, and what happens with no result, since an agent only sees the description, schema, and prior responses. Keep OpenAPI specs updated in the same pull request as API changes, scope agent access with OAuth, and publish a clear answer block naming who builds the tool, how it authenticates, and what it costs. Developers building MCP servers or agent-facing docs can track best practices like these on daily.dev."}}]} ```