# AutomateLab-tech/seo-performance-mcp

**Category:** 🎯 Marketing  
**Repository:** https://github.com/AutomateLab-tech/seo-performance-mcp  
**GitHub Stars:** 2  
**npm Downloads (last month):** 618  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/automatelab-tech-seo-performance-mcp

## Description
Post-publish SEO performance MCP that unifies Google Search Console, Matomo, GA4, Clarity, and AI-citation signals per URL and emits a verdict (refresh / expand / merge / kill / doubledown / hold) per post with reason codes.

## Tools
Capabilities this server exposes over MCP:

- **posts_list** — Discover posts via an XML sitemap (POSTS_SITEMAP_URL or the sitemap_url arg), a JSON override list (POSTS_LIST), or - if configured - the Ghost Admin API. Pass an explicit urls[] to skip discovery entirely.

Returns metadata: url, title, published_at, age_days, tags. Filter by minimum age or published-after date.

When to use: discover which URLs are eligible for snapshot / verdict / cohort analysis. Works with any CMS that exposes a sitemap.
- **posts_snapshot** — Pull a 30/60/90-day snapshot across every configured signal source for one post: GSC clicks/impressions/CTR/position + top queries, Matomo visits + dwell, GA4 pageviews, Clarity scroll/rage clicks, AI-citation counts.

Each source is best-effort: if its env vars are missing the field is omitted. Returns whatever is available.

Read-only. No third-party writes. Optionally persists to the local DuckDB cache when persist=true.
- **posts_decay_curve** — Bucket GSC clicks/impressions/avg-position into ~weekly windows for the last N weeks (default 12) and classify the trend: decay / plateau / growth.

Underpins the verdict engine's decay rules. Read-only GSC query.
- **posts_verdict** — Run the rule-based verdict engine on a single post: combine snapshot + decay curve and emit a verdict with reason codes and a 0-1 confidence score.

Reason codes are deterministic. The mapping reasons -> verdict lives in src/verdict/rules.ts and can be inspected.

Reporting only - does NOT mutate anything. To act on the verdict, hand the brief to a writer or to an AI rewrite tool.
- **posts_refresh_brief** — Produce a markdown brief for a human (or downstream LLM) editor: verdict + reasons + raw numbers + top queries + suggested actions.

Use this as the hand-off artefact when verdict is refresh / expand / merge / double_down.
- **cohort_report** — Run the verdict engine across a cohort (filtered by tag and/or min-age) and return a ranked table sorted by verdict priority then confidence.

Practical use: 'which three posts should I refresh this week?' - the top three rows with verdict=refresh and highest confidence are the answer.
- **posts_cite_loss** — Return the list of LLMs that previously cited this URL but no longer do, with the prior query and last-seen date. Optionally includes the URL that replaced ours.

Requires a configured citation-intelligence MCP endpoint (CITATION_INTELLIGENCE_URL). Otherwise returns an empty list.
- **gsc_quick_wins** — Scan GSC for (page, query) pairs sitting in positions 5-15 with non-trivial impressions and a CTR below their position-expected curve. These are the fastest title-rewrite wins.

Returns top results sorted by impressions desc. Pure GSC pull - platform-agnostic.
- **bing_quick_wins** — Scan Bing Webmaster Tools for queries sitting in positions 5-15 with non-trivial impressions. Bing's index backs Copilot, ChatGPT search, and Perplexity grounding, so a Bing rank gap is an LLM-citation gap.

Query-level only: Bing has no single page+query API, so - unlike gsc_quick_wins, which returns (page, query) pairs - these carry no url. Sorted by impressions desc.

Requires BING_WEBMASTER_API_KEY (Bing Webmaster Tools -> Settings -> API Access). Best-effort: returns config_missing if unset.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "seo-performance-mcp": {
    "command": "npx",
    "args": ["-y","@automatelab/seo-performance-mcp"]
  }
}
```

## Documentation

## 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.

_Full upstream README: https://allmcps.com/mcp/automatelab-tech-seo-performance-mcp/readme_