Seo Performance MCP

What AutomateLab-tech/seo-performance-mcp MCP server does

AutomateLab-tech/seo-performance-mcp MCP server turns post-publish content data into URL-level reports and rule-based recommendations. It can combine Google Search Console performance, Matomo or GA4 analytics, Microsoft Clarity behavior signals, and AI-citation data. Results include raw measurements, reason codes, and, for verdicts, a confidence value from 0 to 1.

The verdict engine returns one of refresh, expand, merge, kill, double_down, or hold. Its rules and thresholds are deterministic and available in src/verdict/rules.ts, so teams can inspect the conditions behind a recommendation. The server reports findings only; it does not edit posts or write to third-party platforms.

How it works

Use posts_list to identify eligible content from an XML sitemap, a POSTS_LIST JSON array, or an optionally configured Ghost Admin API. You can also provide URLs directly and bypass discovery. Metadata may include the title, publication date, age, tags, and other available post fields.

For a selected URL, posts_snapshot gathers data over a 30-, 60-, or 90-day window. posts_decay_curve groups recent Search Console data into roughly weekly buckets and labels the trend as decay, plateau, or growth. posts_verdict combines the snapshot and decay results. cohort_report applies the same process to a filtered group and ranks the output by verdict priority and confidence.

The server also provides focused reports. gsc_quick_wins finds page-and-query combinations ranking from positions 5 through 15 with weaker-than-expected click-through rates. bing_quick_wins identifies comparable Bing query opportunities but does not include page URLs. posts_cite_loss reports LLMs that stopped citing a URL when a citation-intelligence endpoint is configured.

Setup and configuration

Install the MCP package with npx -y @automatelab/seo-performance-mcp and add it to an MCP client configuration. The README names Claude Desktop, Claude Code, and Cursor as supported client contexts; the tools can also be run through the included seo-perf-cli command or from a scheduled GitHub Action.

All environment variables are optional. POSTS_SITEMAP_URL is the usual discovery input. Other supported configuration includes POSTS_LIST, Ghost Admin credentials, Google Search Console service-account data and site URL, Matomo URL/token/site ID, GA4 property and service-account data, Clarity project credentials, CITATION_INTELLIGENCE_URL, and BING_WEBMASTER_API_KEY. Missing configuration skips the related adapter rather than preventing startup. The exact data available to a verdict therefore depends on the configured sources.

Tools and capabilities

AutomateLab-tech/seo-performance-mcp MCP server exposes tools for:

• Listing posts and filtering by age or publication date.
• Building unified URL snapshots.
• Measuring Search Console decay trends.
• Producing verdicts, reason codes, confidence scores, and editor briefs.
• Ranking cohorts for content-audit work.
• Finding Search Console and Bing quick wins.
• Comparing current and previous AI citations.

posts_refresh_brief creates Markdown containing the verdict, evidence, top queries, and suggested editorial actions. A local DuckDB cache can be used when persistence is enabled.

Limitations and notes

Every source is best-effort. A missing environment variable removes that source’s fields, and citation-loss analysis returns an empty list without CITATION_INTELLIGENCE_URL. Bing quick wins are query-level because the described Bing API does not provide a single page-and-query result in this workflow.

The recommendations are rule-based rather than generated by a predictive model. They are intended as reporting and editorial hand-off artifacts; applying a refresh, merge, rewrite, or other change must happen in a separate system. AutomateLab-tech/seo-performance-mcp MCP server does not mutate posts or external analytics platforms.