Seo Monitor logo

Seo Monitor

Organization
cognyai
seo-monitor

Monitor SEO rankings, queries, and indexing via Search Console and/or Bing Webmaster Tools MCP

Overview

Publishercognyai
Repositoryclaude-code-marketing-skills
Skill nameseo-monitor
Stars
111
Forks
15
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by cognyai on GitHub. Read the source before you install it.

Installation

Install the Seo Monitor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/seo-monitor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cognyai/claude-code-marketing-skills.git /tmp/claude-code-marketing-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-marketing-skills/skills/seo-monitor .claude/skills/seo-monitor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seo Monitor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Seo Monitor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Seo Monitor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SEO Monitor

Monitor your website's search performance using live Google Search Console data via Cogny's MCP server.

Requires: Cogny Agent subscription ($9/mo) — Sign up

Works with

JobPrimaryAlso answers itWhat differs
Queries, pages, CTR, positionGoogle Search ConsoleBing Webmaster ToolsBing data covers Bing and Copilot; positions and CTR are not comparable across engines, so report them side by side
Indexing / crawl healthGSC (tool_inspect_url, tool_get_sitemaps)Bing (tool_get_crawl_issues, tool_get_crawl_stats)GSC inspects one URL at a time; Bing lists issues site-wide
Spot-check a rank todaycogny-brave-search—Independent index, 1 credit per call
AI answer-engine trendcogny-ai-visibility history—Only prompts already checked (e.g. by /seo-audit); reading history is free

Prerequisites Check

If no mcp__cogny__* tools exist (no list_integrations, no cogny_status), print this and stop:

SEO Monitor needs your marketing data through Cogny's MCP gateway.

1. Sign up at https://cogny.com and connect Google Search Console and/or Bing Webmaster Tools.
2. Add Cogny to .mcp.json in your project:
   {"mcpServers": {"cogny": {"type": "http", "url": "https://app.cogny.com/mcp"}}}
3. Restart Claude Code; it opens a browser for the OAuth login on first use.

Without Cogny you can still: run /seo-audit <url> for a one-time audit on public data.

Otherwise call mcp__cogny__list_integrations. You need Google Search Console or Bing Webmaster Tools (either is enough; both is better). Flag any whose health_status is not healthy, then make one cheap read per integration (GSC tool_list_properties, Bing tool_get_sites): a 401, Forbidden or scope error is 🔴 "reconnect ", with no retry. health_status misses revoked tokens. Cogny-native servers (cogny-brave-search, cogny-ai-visibility) don't appear in list_integrations; treat them as available if their tools load.

If a Bing tool listed here is missing (older connections cache a short list without tool_get_query_stats / tool_get_page_stats), call mcp__cogny__refresh_mcp_discovery once. New tools only load after the client reconnects, so for this run use tool_get_traffic_stats (site-level daily clicks and impressions; use its average position only if the rows include one, otherwise report Bing position as n/a) instead, mark Bing ⚠ "needs reconnect", and tell the user to reconnect the Cogny MCP. Never loop on refresh.

If neither is connected, say "connect Google Search Console or Bing Webmaster Tools in Cogny" and stop.

Usage

/seo-monitor — full overview /seo-monitor queries — top queries and ranking changes /seo-monitor pages — top pages performance /seo-monitor indexing — indexing status and issues

Steps

GSC lag rule: Search Console data lags about 3 days. Every GSC window ends 3 days ago (e.g. current = the 28 days ending today − 3, previous = the 28 days before that), or the latest days read as a false drop. Keep row_limit at 500 or less; bigger query pulls get very large.

1. Query Performance (last 28 days)

  • GSC: mcp__cogny__mcp__Google_Search_Console__tool_get_search_analytics with site_url, start_date, end_date, dimensions: ["query"]; run again for the previous 28 days.
  • Bing: mcp__cogny__mcp__Bing_Webmaster_Tools__tool_get_query_stats (site_url). It returns weekly rows; split them into the two periods yourself. If it isn't loaded, fall back to tool_get_traffic_stats (site_url) for site-level totals only and mark Bing queries ⚠ "needs reconnect". It returns one row per day over a long history: keep only the rows whose date falls in the current and previous windows (same dates as GSC), sum clicks and impressions per window, and report the two totals, never the raw rows. Bing position: the rows' average if present, otherwise n/a.

Pull top queries by clicks:

  • Query text, clicks, impressions, CTR, average position
  • Compare vs previous 28 days: which queries are rising/falling?

2. Page Performance

GSC: same call with dimensions: ["page"]. Bing: tool_get_page_stats (site_url); if it isn't loaded, report Bing pages as ⚠ "needs reconnect" (the tool_get_traffic_stats totals from step 1 still stand).

Top pages by clicks:

  • URL, clicks, impressions, CTR, avg position
  • Identify pages losing traffic (position drops)
  • Find pages with high impressions but low CTR (title/description optimization opportunities)

3. Ranking Changes

Compare current vs previous period:

  • New queries appearing (opportunities)
  • Queries losing position (threats)
  • Queries near page 1 (positions 11-20 — quick wins)
  • Optional spot-check: for the 3-5 biggest movers, mcp__cogny__mcp__cogny-brave-search__tool_brave_rank_check (domain, query, country) to confirm today's position outside Google
  • Optional AI trend: mcp__cogny__mcp__cogny-ai-visibility__tool_get_ai_visibility_history (brand, days: 90). Report mention rate per engine only if history exists; don't start new paid checks here

4. Indexing Status

GSC: tool_get_sitemaps for which sitemaps are submitted, when they were last read, and their errors/warnings. Its indexed count comes back 0 because the API doesn't fill it, so don't report "submitted vs indexed" from it. Do compare each sitemap's submitted count with the live sitemap's URL count:

bash
curl -sL -A "Mozilla/5.0" "<sitemap path from tool_get_sitemaps>" | grep -o '<loc>' | wc -l

For a sitemap index, count the <loc> entries of each child sitemap and sum. A gap of more than ~10% means Google last read an older version (check lastDownloaded) or the sitemap changed since; flag it 🟡 and suggest resubmitting (a write, so ask first). Instead sample tool_inspect_url on 10–20 URLs (new pages, falling pages, and a few from each sitemap) and report "N/M sampled URLs indexed" with each failing URL's coverageState. Bing: tool_get_crawl_issues and tool_get_crawl_stats.

Check:

  • Indexed share of the sampled URLs (GSC) and Bing's crawled/indexed counts
  • Pages with indexing errors
  • Pages excluded from indexing
  • New pages discovered

5. Report

SEO Monitor: [Site]
Period: [dates]

Search Performance (Google Search Console | Bing Webmaster, side by side):
Clicks: [X] ([+/-]% vs prev)
Impressions: [X] ([+/-]%)
Avg CTR: [X]% ([+/-])
Avg Position: [X] ([+/-])

Top 5 Queries:
1. [query] — pos [X], [X] clicks
...

Rising Queries (opportunity):
- [query]: position improved [X] → [Y]
...

Falling Queries (threat):
- [query]: position dropped [X] → [Y]
...

Quick Wins (position 11-20, high impressions):
- [query] at pos [X] with [Y] impressions — optimize [page URL]
...

Top 3 Actions:
1. ...
2. ...
3. ...

Writes (Google_Search_Console__tool_submit_sitemap, Bing_Webmaster_Tools__tool_submit_url) are never pre-approved. Ask first, e.g. "Submit the 4 new URLs to Bing?"

Recording findings

Use create_ticket when the workspace has it (Cloud) and create_finding otherwise (Solo). The fields differ; see section 2 of ../marketing-engineer/references/mcp-routing.md.

Frequently asked questions

What does the Seo Monitor AI skill do?

Monitor SEO rankings, queries, and indexing via Search Console and/or Bing Webmaster Tools MCP

Why use Seo Monitor on TypingMind?

Because you install it once and use it with any model. Seo Monitor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Seo Monitor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/seo-monitor. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Seo Monitor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Seo Monitor?

As many as you like. As long as a model supports skills, you can use Seo Monitor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Seo Monitor AI skill free?

It is published on GitHub by cognyai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇