Back to cookbook

ChatGPT Prompt to Audit Webflow CMS Content for SEO Gaps via Webflow's MCP Server

0 views Updated

Make this prompt yours

Share

This ChatGPT prompt for auditing Webflow content reads your actual CMS collection items through Webflow's MCP server and flags SEO gaps - missing meta descriptions, thin pages, duplicate title tags - directly against the live site structure instead of a static export you'd have to pull by hand. It's built for content managers, SEO specialists, and small marketing teams running a site on Webflow who want a recurring content audit without logging into every page one by one.

Webflow's MCP server gives a connected model read access to your actual CMS collections, page settings, and site structure, so the SEO audit reflects what's really published, not a guess based on a sitemap scrape or a few pasted URLs. The model can cross-reference multiple collection items at once, which is where manual audits usually break down past 20 or 30 pages.

The prompt still relies on the model's judgment about what counts as "thin" or "duplicate," so treat its output as a prioritized checklist to verify, not a final ranking. If you're running this audit across dozens of templated collection pages, Context Extractor is worth pairing with it to pull just the relevant CMS fields instead of feeding the model your entire content export at once.

Prompt template

Make this prompt yours

prompt-template
268 tokens
ROLE: You are an SEO content auditor with read access to a Webflow site's CMS collections through an MCP connection. CONTEXT: - Site/collection to audit: [COLLECTION NAME, e.g. Blog Posts] - Target keyword focus: [DESCRIBE PRIMARY TOPICS OR KEYWORDS THE SITE RANKS FOR OR WANTS TO RANK FOR] - Number of items to review: [NUMBER OR "all"] TASK: 1. Pull the title, meta description, word count, and slug for each item in the specified collection. 2. Flag items missing a meta description or with one under [NUMBER] characters. 3. Flag items with duplicate or near-duplicate title tags across the collection. 4. Flag items under [WORD COUNT] words as potentially thin content. 5. Rank all findings by severity: critical, moderate, minor. CONSTRAINTS: - Only report on data actually retrieved from the collection - do not guess at content you were not given - Reference each flagged item by its exact slug or URL - Do not recommend specific rewritten copy unless asked - this audit identifies issues, it does not fix them OUTPUT FORMAT: Severity: [critical/moderate/minor] Page: [slug or URL] Issue: [specific problem] Recommended fix direction: [one sentence, no full rewrite]

Want it sharper? Optimize this prompt with Prompt Optimizer, check it with the Prompt Debugger or shorten it with the Token Optimizer.

Example input

example-input
27 tokens
Collection to audit: Blog Posts (34 items) Target keyword focus: small business accounting software comparisons Number of items to review: all

When to use it

  • You run a Webflow site with a CMS collection (blog, product pages, locations) that's grown past the point of manually checking each page's SEO basics
  • You want a recurring quarterly or monthly content audit without exporting data into a separate spreadsheet tool first
  • You suspect duplicate or near-duplicate title tags and meta descriptions across templated collection pages
  • You're prioritizing which existing pages to update before writing any new content

Best practices

  • Specify which CMS collections to audit by name rather than asking the model to check "the whole site," which can time out or produce a shallow pass
  • Ask for a severity ranking (critical, moderate, minor) instead of a flat list, so you know what to fix first
  • Request specific page URLs or slugs in the output, not just descriptions, so you can act on the findings directly in Webflow
  • Re-run the audit after fixes to confirm the flagged issues were actually resolved rather than assuming they were

Common mistakes

  • Asking the model to audit the entire site in one pass instead of one collection at a time, which produces vague, unprioritized output
  • Not specifying your target keyword strategy, so the model flags generic SEO issues instead of gaps relevant to your actual ranking goals
  • Treating every flagged "duplicate" as an immediate must-fix without checking whether the pages are genuinely meant to be similar
  • Skipping a re-audit after making changes, so recurring issues go unnoticed

FAQs

Can ChatGPT actually see my live Webflow content, or do I have to paste it in manually?

With Webflow's MCP server connected, the model can read your actual CMS collection data directly - you don't need to export or paste content in for this to work.

How many pages can this prompt realistically audit at once?

It depends on your model's context limits and how much data each page carries, but auditing one collection at a time (rather than an entire multi-collection site) keeps results specific and prioritized instead of shallow.

Does this prompt fix the SEO issues it finds?

No - it's intentionally scoped to identify and rank issues. Fixing titles, meta descriptions, or thin content is a separate step so you can review before anything changes on the live site.

How can I check this prompt's quality before using it on a large Webflow site?

Intelligence Score - run the filled-in prompt through it first to catch vague instructions or missing constraints before pointing it at dozens of live CMS pages.

Found this prompt useful? Share it.

Share

More in Content & SEO

Content & SEO

AI Prompt to Audit Blog Content for SEO via HubSpot's MCP Server

This HubSpot MCP prompt is for content marketers and SEO leads who want ChatGPT or Claude to pull live blog post data straight out of HubSpo…

ROLE: You are an SEO editor reviewing a blog post pulled from HubSpot via its MCP server.

CONTEXT:
- Post title: [POST_TITLE]
- Post slug: [POST_SLUG]
- Target keyword: [TARGET_KEYWORD]
- Current meta description: [META_DESCRIPTION]
- Word count: [WORD_COUNT]
- Topic cluster / related posts: [RELATED_POST_TITLES]
- Full post body (via HubSpot MCP read): [POST_BODY]

TASK:
Audit this post for on-page SEO issues using only the data above. Check specifically for:
1. Whether the title and meta description match the target keyword's search intent
2. Whether the meta description is within 120-160 characters and includes the target keyword
3. Header structure problems (missing H2/H3s, headers that don't match what the section actually covers)
4. Thin or underdeveloped sections relative to top-ranking content for this keyword
5. Missing internal links to or from the related posts listed above

CONSTRAINTS:
- Do not invent metrics, rankings, or competitor data you were not given
- If a required field above is missing or empty, say so explicitly instead of guessing
- Keep recommendations specific to this post, not generic SEO advice

OUTPUT FORMAT:
- A short summary verdict (Strong / Needs Work / Weak)
- A prioritized list of 3-6 specific fixes, each one sentence
- A separate line listing any internal link opportunities by post title

Make this prompt yours

Content & SEO

AI Prompt to Turn a Blog Post Into a Twitter/X Thread

This AI prompt for repurposing a blog post into a Twitter/X thread is built for content marketers, bloggers, and solo creators who already h…

ROLE: You are a social media copywriter who specializes in turning long-form content into high-performing Twitter/X threads.

CONTEXT:
Source blog post or article: [PASTE FULL BLOG POST TEXT HERE]
Target audience: [DESCRIBE WHO WILL READ THIS THREAD]
Voice/tone to match: [E.G., CASUAL AND DIRECT / PROFESSIONAL AND AUTHORITATIVE]
Goal of the thread: [E.G., DRIVE CLICKS BACK TO THE FULL POST / STAND ALONE AS VALUABLE CONTENT]

TASK:
1. Identify the single most compelling hook, insight, or claim in the source content.
2. Generate 3-5 alternative opening tweets built around that hook, each using a different angle (question, bold claim, contrarian take, specific number/result).
3. Once the opening is chosen, break the rest of the article into a logical sequence of [NUMBER] tweets that build the argument step by step.
4. Write a closing tweet that includes a clear call to action: [E.G., LINK BACK TO FULL POST / ASK A QUESTION / INVITE REPLIES].

CONSTRAINTS:
- Each tweet must stay under 280 characters, including spaces and punctuation.
- Each tweet must make sense as a standalone statement, not require the previous tweet for context.
- Do not use hashtags unless explicitly requested.
- Match the specified voice and tone throughout, not just in the opening tweet.
- Number each tweet (1/, 2/, etc.) at the start.

OUTPUT FORMAT:
First, list the 3-5 candidate opening tweets under the heading "OPENING OPTIONS."
Then, under the heading "FULL THREAD," output the complete numbered thread starting from your recommended opening tweet through the closing call-to-action tweet.

Make this prompt yours

Content & SEO

SaaS Onboarding Email Sequence

This prompt writes a three email onboarding sequence built around one goal: getting a new user to their first win fast. Each email has a sin…

Write a 3-part email onboarding sequence for a B2B SaaS product called [PRODUCT], used by [AUDIENCE] to [MAIN OUTCOME].

Activation goal: [THE ONE ACTION THAT MATTERS]

Email 1: Welcome and quick win (send immediately).
Email 2: Discover the core feature (send day 2).
Email 3: Invite to the community or webinar (send day 4).

For each email give: 3 subject lines, preview text, body under 150 words, one call to action.
Tone: conversational, helpful, concise. No hype words.

Make this prompt yours