MongoDB scores 68/100 (Grade D), passing 11 of 22 checks (50%). There are 8 issues limiting AI agent readiness. Addressing llms.txt support and markdown availability would provide the most improvement.
# Agent Score Fix Report — MongoDB URL: https://www.mongodb.com/docs Score: 68/100 (Grade D) I need help improving the AI-readiness of the documentation at https://www.mongodb.com/docs. Agent Score found 6 failing checks and 2 warnings. ## Failing Checks (6) - [content-discoverability] Llms Txt Size: llms.txt is 4,561,591 characters (exceeds 100,000 threshold; will be truncated by most agents) - [content-discoverability] Llms Txt Directive: No llms.txt directive found in any of 9 sampled pages; 1 failed to fetch - [markdown-availability] Content Negotiation: Server ignores Accept: text/markdown header (0/10 sampled pages return markdown) - [page-size] Page Size Html: 10 of 10 sampled pages convert to over 100K chars (max 373K, 34% boilerplate) - [page-size] Content Start Position: 10 of 10 sampled pages have content starting past 50% (worst 98%) - [observability] Markdown Content Parity: 2 of 9 pages have substantive content differences between markdown and HTML (avg 14% missing) ## Warnings (2) - [content-discoverability] Llms Txt Links Markdown: Same-origin links point to HTML, but 10 have .md variants available (1 external link excluded) - [page-size] Rendering Strategy: 1 of 10 sampled pages have server-rendered page structure but little substantive content; agents will see headings and navigation but not the page's actual documentation ## Fix Instructions For each issue above, please: 1. Analyze the documentation site at https://www.mongodb.com/docs 2. Implement the specific fix 3. Verify the fix would cause the check to pass ### Common fixes: - **No llms.txt**: Create /llms.txt following https://llmstxt.org — list all doc pages in markdown format - **No .md URL support**: Configure your docs platform to serve pages at equivalent .md URLs (e.g. /docs/quickstart.md) - **No content negotiation**: Return markdown when request includes Accept: text/markdown header - **Large page size**: Reduce nav boilerplate, inline scripts, and repetitive markup - **No sitemap**: Generate /sitemap.xml listing all documentation URLs - **Auth walls**: Ensure docs pages return 200 without requiring login cookies or tokens - **No Last-Modified header**: Configure your server/CDN to include Last-Modified response headers - **Tab content hidden**: Ensure tabbed content is rendered in the HTML (not JS-only) so agents can read all variants ## Run afdocs Locally for More Detail To get deeper visibility into what's failing, run afdocs against your docs: npx afdocs https://www.mongodb.com/docs --fixes --verbose - **--fixes**: Adds "Fix:" lines to the output for each warn/fail check with actionable remediation steps - **-v, --verbose**: Shows per-page details (specific URLs, character counts, error codes) for checks with issues — useful for per-URL visibility into what's failing
CHECK RESULTS
How your docs scored
markdown-content-parity2 of 9 pages have substantive content differences between markdown and HTML (avg 14% missing)
cache-header-hygieneAll 12 endpoints have appropriate cache headers
llms-txt-freshnessSitemap has 45690 URLs but none are under the docs path prefix (/docs)
page-size-html10 of 10 sampled pages convert to over 100K chars (max 373K, 34% boilerplate)
content-start-position10 of 10 sampled pages have content starting past 50% (worst 98%)
rendering-strategy1 of 10 sampled pages have server-rendered page structure but little substantive content; agents will see headings and navigation but not the page's actual documentation
page-size-markdownAll 9 pages under 50K chars (median 11K, max 21K)
content-negotiationServer ignores Accept: text/markdown header (0/10 sampled pages return markdown)
markdown-url-support9/10 sampled pages support .md URLs (90%)
auth-gate-detectionAll 10 sampled pages are publicly accessible
auth-alternative-accessAll docs pages are publicly accessible; no alternative access paths needed
llms-txt-sizellms.txt is 4,561,591 characters (exceeds 100,000 threshold; will be truncated by most agents)
llms-txt-directiveNo llms.txt directive found in any of 9 sampled pages; 1 failed to fetch
llms-txt-links-markdownSame-origin links point to HTML, but 10 have .md variants available (1 external link excluded)
llms-txt-existsllms.txt found at 2 location(s)
llms-txt-validllms.txt follows the proposed structure (H1, blockquote, heading-delimited link sections)
llms-txt-links-resolveAll 10 same-origin sampled links resolve (21329 total links)
tabbed-content-serialization16 tab group(s) across 2 of 10 sampled pages; all serialize under 50K chars
markdown-code-fence-validityAll 108 code fences properly closed across 11 pages
section-header-quality2 page(s) with tabs found, but no section headers inside tab panels to evaluate
http-status-codesAll 10 sampled pages return proper error codes for bad URLs
redirect-behaviorAll 3 redirect(s) across 10 sampled pages are same-host HTTP redirects
