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 g-battaglia/mcp-seo --skill mcp-seogit clone --depth 1 https://github.com/g-battaglia/mcp-seoWrote 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/g-battaglia/mcp-seo/mcp-seo)<a href="https://agentmods.dev/skills/g-battaglia/mcp-seo/mcp-seo"><img src="https://agentmods.dev/badge/skills/g-battaglia/mcp-seo/mcp-seo/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/g-battaglia/mcp-seo/mcp-seo"><img src="https://agentmods.dev/badge/skills/g-battaglia/mcp-seo/mcp-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00207 | $0.01908 |
| Opus 5 | $0.00103 | $0.00954 |
| Sonnet 5 | $0.00041 | $0.00382 |
| Haiku 4.5 | $0.00021 | $0.00191 |
Grade A, and why
mcp-seo scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Schema markup detection**: `web_fetch` and `curl` cannot reliably detect JSON-LD injected via JavaScript. Use `analyze_structured_data` instead — it renders the page with a headless browser. How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP-SEO — SEO Analysis Toolkit for AI Agents
You have access to mcp-seo, a complete SEO analysis toolkit with 18 MCP tools and 21 CLI commands. Use these tools to perform real analysis on any URL — do not guess or assume SEO issues, run the tools and report actual findings.
Prerequisites
The user must have mcp-seo installed. If tools fail with "command not found":
pip install mcp-seo # Install the package
mcp-seo setup # Install headless Chromium (one-time)
MCP Server Configuration
If using as an MCP server (Claude Desktop, Cursor, etc.), add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-seo": {
"command": "mcp-seo",
"args": ["mcp"]
}
}
}
Tool Reference
If the mcp-seo MCP server is connected, use MCP tool names directly. Otherwise, use CLI commands via bash.
Page Fetching
| MCP Tool | CLI Command | What it does |
|---|---|---|
crawl |
mcp-seo crawl <url> |
Render page with headless Chromium, return full HTML |
fetch_page |
mcp-seo fetch <url> |
Raw HTTP response (headers, status, redirects, SSL) |
On-Page SEO
| MCP Tool | CLI Command | What it does |
|---|---|---|
analyze_meta_tags |
mcp-seo meta <url> |
Title, description, OG, Twitter, canonical, viewport, hreflang |
analyze_headings |
mcp-seo headings <url> |
H1-H6 hierarchy, single H1 check, skip-level detection |
analyze_links |
mcp-seo links <url> |
Internal/external count, nofollow, anchor text, broken links |
analyze_images |
mcp-seo images <url> |
Alt text, lazy loading, dimensions, WebP/AVIF, srcset |
analyze_content |
mcp-seo content <url> |
Word count, Flesch-Kincaid readability, keywords, n-grams |
Technical SEO
| MCP Tool | CLI Command | What it does |
|---|---|---|
analyze_headers |
mcp-seo headers <url> |
Cache headers, HSTS, CSP, SSL cert, cookie security |
analyze_sitemap |
mcp-seo sitemap <url> |
XML sitemap discovery, parsing, validation (50K URL limit) |
analyze_robots |
mcp-seo robots <url> |
robots.txt rules, user-agent blocks, crawl-delay, sitemap directives |
analyze_structured_data |
mcp-seo structured-data <url> |
JSON-LD, Microdata, RDFa extraction and validation |
analyze_url_structure |
mcp-seo url-structure <url> |
URL length, depth, separators, tracking params, session IDs |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 192 lines · 207 tokens per session scan A 113cc00e25aa
mcp-seo is a skill published in the GitHub repository g-battaglia/mcp-seo (1 stars, last pushed 5mo ago), licensed MIT. It adds 207 tokens to every session and 1,908 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…