mcp-gsc is an MCP server that connects Google Search Console, a service for inspecting website search performance, to AI assistants so users can ask questions about SEO data in natural language. SEO professionals use it to analyze their Google Search Console data, and the catalogue entries provide related skills, a plugin, an instruction, and MCP configuration.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AminForou/mcp-gsc --skill cannibalization-checkgit clone --depth 1 https://github.com/AminForou/mcp-gscWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aminforou/mcp-gsc/cannibalization-check)<a href="https://agentmods.dev/skills/aminforou/mcp-gsc/cannibalization-check"><img src="https://agentmods.dev/badge/skills/aminforou/mcp-gsc/cannibalization-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aminforou/mcp-gsc/cannibalization-check"><img src="https://agentmods.dev/badge/skills/aminforou/mcp-gsc/cannibalization-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00298 |
| Opus 5 | $0.00018 | $0.00149 |
| Sonnet 5 | $0.00007 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
cannibalization-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
4 near-identical copies found in the catalogue:
- cannibalization-check — 100% identical, 0 lines differ
- cannibalization-check — 100% identical, 0 lines differ
- cannibalization-check — 100% identical, 0 lines differ
- cannibalization-check — 86% identical, 4 lines differ
What it actually says
Keyword Cannibalization Check
Identify queries where multiple pages on the same site are competing for rankings.
Steps
- Call
list_propertiesto confirm the exactsite_url. - Call
get_advanced_search_analyticswithdimensions=query,page,sort_by=impressions,row_limit=1000to get all query+page combinations. - Group rows by
query. Queries with two or more distinct pages in the top results are cannibalization candidates. - For each cannibalizing query, collect: both page URLs, their individual clicks, impressions, CTR, and position.
- Sort candidates by total impressions (most valuable cannibalization conflicts first).
- Limit the output to the top 20 most severe cases.
Output format
For each cannibalization case:
- Query: the competing keyword
- Pages: list each URL with its metrics
- Severity: High / Medium / Low based on impressions at stake
- Recommendation: which page to consolidate to (pick the one with better position or CTR), and whether to use a canonical, redirect, or content merge
Present as a markdown table followed by a prioritized action list.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 29 lines · 37 tokens per session scan A 8ffa01e1c025
cannibalization-check is a skill published in the GitHub repository AminForou/mcp-gsc (1,511 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 298 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
google-search-console-cli
Google Search Console data analysis and site management via google-search-console-cli. Use when the user wants to check search performance, analyze queries, inspect URL index status, manage sitemaps, or view site properties. Triggers: "Search Console", "search performance", "search queries", "GSC", "index status"…
find-a-paid-api
Search 14,700 x402-payable HTTP endpoints by capability, chain, host and maximum price. Use when an agent needs an API it can pay for per call with USDC, wants to know what a call costs before making it, or is looking for machine-payable data sources.
find-an-mcp-server
Search 10,000 remotely-callable MCP servers by capability, transport, host and whether they need credentials. Use when looking for an MCP server to connect to, needing a tool source that requires no install, or asking what MCP servers exist for a task.
grade-a-site
Grade any public URL for agent-readability across 20 checks and get paste-ready fixes. Use when asked whether a site is readable by AI agents, why an agent cannot use a site, or how to make a site discoverable to LLMs and agents.
list-a-product
Register an AI product, API, agent or MCP server in a public directory autonomously, with no human approval step. Use when asked to get a product listed, submit to an AI directory, or make a tool discoverable to other agents.
balzac-mcp
Balzac MCP server gives AI assistants native tool access to the Balzac content platform — manage workspaces, keywords, suggestions, articles, integrations, and more through structured MCP tool calls instead of CLI commands.