This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Give Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP-aware AI tool direct access to the SEO Score API: full audits, backlink data, monitoring, and history.
npx -y seoscoreapi-mcpSet your API key once and forget it:
export SEO_SCORE_API_KEY="ssa_your_key_here"(Get a free key at https://seoscoreapi.com — no card required.)
Related MCP server: polaris-audit
Tool | What it does | Plan |
| Full SEO audit on a URL — score, grade, 80+ checks, AI readability, prioritized fixes. | Free |
| Audit up to 10 URLs at once ( | Starter ($5/mo) |
| Current plan + monthly usage + remaining quota | Free |
| Public shareable HTML report for a domain | Free |
| Add a URL to scheduled re-audit + alerts | Starter |
| List monitored URLs | Starter |
| Time-series of past scores for a URL | Starter |
| Every domain audited by this key with 30-day trend | Starter |
| Observed backlinks for a domain (audit-fed graph; honest data caveat in every response) | Basic ($15/mo) |
| Deep Site Audit: 9 dimensions, thousands of catalog checks + up to 150 AI checks; waits for the result ( | Pro ($39/mo), Ultra, or credits |
| Queue a Deep Site Audit and return its | same |
| Status of a Deep Site Audit job, with the | same |
| Deep Site Audits used and remaining this month | same |
| Remove a URL from score monitoring | Starter |
| Structured diff across 2-5 URLs | Basic ($15/mo) |
| Head-to-head against a competitor's page for a keyword | Pro ($39/mo) |
| ADA / WCAG 2.1 AA audit: score, lawsuit risk, violations with fixes ( | Paid plans; own monthly allowance |
| How well AI/LLM systems can consume a page | Any key |
| Third-party trackers and pixels a page loads | Any key (one audit) |
| Conversion score: headline, CTA, trust, forms, objections | Any key (one audit); full fix list on paid plans |
| Page-2 quick wins from Search Console rows or CSV you pass in | Any key (one audit) |
| Generate an llms.txt file for a domain | No key needed; curated version on Basic+ |
| GEO audit: how visible a page is to LLMs | Basic |
| How often LLMs mention a brand | Basic |
| GEO monitoring | Basic |
| Multi-page site crawl (broken pages, redirects, duplicates, orphans, slow pages); waits for the result | Pro, Ultra, or a Deep Audit credit |
| Start a crawl and poll it yourself | same |
| Prompts to track for AI citations | Any key; not metered |
| Track a brand across ChatGPT, Gemini, Perplexity and Claude | Starter ($5/mo) |
| Run a tracker, read a run, read the trend | Starter; metered in checks |
| One-off citation check for a brand and one prompt | Paid plans; metered per check |
| Top-up packs and the account's check balance | Any key |
| Stripe Checkout link for a top-up pack (charges nothing until the user pays it) | Paid plans |
| Read the auto-reload setting | Any key; read-only |
Report files (GET /audit/export): the PDF is binary and an MCP tool result is text.
The audit tool returns the same data as JSON; use the REST API or the Python / Node
SDK (audit_export / auditExport) for the file.
Turning auto-reload on. The API has no such endpoint for API keys: it authorizes
charges, so it is set from the dashboard only. citation_auto_reload reads it.
Account actions (/signup, /verify, /upgrade, /rotate-key) and the public
scoreboard opt-out.
Env var | Default | Purpose |
| (none) | Your API key |
|
| API host |
|
| Deep Audit host ( |
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"seoscoreapi": {
"command": "npx",
"args": ["-y", "seoscoreapi-mcp"],
"env": {
"SEO_SCORE_API_KEY": "ssa_your_key_here"
}
}
}
}Restart Claude Desktop. You'll see the SEO Score tools in the tool picker.
claude mcp add seoscoreapi -e SEO_SCORE_API_KEY=ssa_your_key_here -- npx -y seoscoreapi-mcpOpen Cursor Settings → MCP Servers → Add a new server with the same JSON shape as Claude Desktop above.
Settings → Cascade → MCP Servers → paste the same configuration.
Run npx -y seoscoreapi-mcp as a stdio transport. The server speaks standard MCP and exposes all tools in the table above.
Once installed, talk to your AI assistant naturally:
"Audit https://stripe.com and tell me the top 3 things to fix."
"Run a batch audit on stripe.com, square.com, and adyen.com, then compare their AI readability scores."
"What backlinks have we seen pointing at my-startup.com?"
"Check the score history for our marketing site over the last 30 days."
"Run a deep audit on my-startup.com as a SaaS site and list the high-severity findings."
"Run an accessibility audit on our pricing page and list the critical WCAG failures."
"Crawl my-startup.com and show me the broken links and orphan pages."
"Build starter prompts for 'SEO audit API', create a citation tracker for Acme, and run it."
The tool the AI picks is shown in your client; you can always ask "what tools did you use?" to see the trace.
MCP lets the AI reach data it wouldn't have — your actual site SEO scores, the backlink graph, your monitoring history — without any custom plumbing. Every prompt that says "audit this URL" goes from idea to result in one round-trip. Same source of truth as the REST API; no copying scores between tools.
The backlinks tool returns an audit-fed sample, not a comprehensive backlink index. Every response includes a data_caveat explaining exactly what the dataset is. We are not Ahrefs and don't pretend to be — we expose the unique, growing graph our customers' audits build for free.
The MCP server is open source: https://github.com/SeoScoreAPI/seoscoreapi-mcp
MIT
This server cannot be deployed
SEO, broken links, Lighthouse, sitemaps, Open Graph tags and SSL expiry for any list of URLs.
Free SEO, GEO, and AEO audits: analyze any page or domain, AI-crawler access, agent readiness.
Audit public webpages and supplied markup for HTML, CSS, SEO, JSON-LD, and link issues.
Technical SEO, passive security and page-delivery audits with evidence and suggested fixes.
