Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SEO Audit MCP run full audit on https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A comprehensive SEO auditing tool suite. Run audits via CLI, Local MCP (stdio), or Remote MCP (HTTP).
Check | What It Detects |
Meta Tags | Missing/invalid title, description, viewport, Open Graph tags |
Sitemap | Validate |
Robots.txt | Validate |
Broken Links | Scan page for broken/404 links |
Headings | Analyze h1–h6 hierarchy compliance |
Duplicate Titles | Detect duplicate or poorly formed page titles |
Keyword Density | Analyze keyword frequency and density |
Related MCP server: Keytomic MCP
All packages are published to npm under the @seo-audit scope.
Package | npm | Description | Type |
| Shared audit logic | Library | |
| Command-line interface ( | CLI | |
| MCP server over stdio ( | MCP (local) | |
| MCP server over HTTP ( | MCP (remote) |
# CLI — audit any website
npx @seo-audit/cli https://example.com
# Local MCP — run as an MCP server
bunx @seo-audit/local-mcpnpm install -g @seo-audit/cli
seo-audit https://example.comnpm install -g @seo-audit/local-mcp
seo-audit-mcpseo-audit [options] <url>
Arguments:
url Website URL to audit (e.g. https://example.com)
Options:
-c, --checks <checks> Comma-separated checks to run.
Available: meta-tags, sitemap, robots-txt,
broken-links, headings, duplicate-titles,
keyword-density
-t, --timeout <ms> Request timeout (default: 15000)
-C, --concurrency <n> Concurrency for link checking (default: 5)
-j, --json Output as JSON
-V, --version Show version
-h, --help Display help# Full audit
npx @seo-audit/cli https://example.com
# Specific checks only
npx @seo-audit/cli https://example.com --checks meta-tags,headings
# JSON output
npx @seo-audit/cli https://example.com --json
# Higher timeout for slow sites
npx @seo-audit/cli https://example.com --timeout 30000Add to claude.json:
{
"mcpServers": {
"seo-audit": {
"command": "bunx",
"args": ["@seo-audit/local-mcp"]
}
}
}Add to opencode.json:
{
"mcp": {
"seo-audit": {
"type": "local",
"command": ["bun", "x"."-y", "@seo-audit/local-mcp"],
"enabled": true
}
}
}Once connected, the following tools are available:
Tool | Description |
| Run all SEO checks (or subset) |
| Check meta tags |
| Validate sitemap.xml |
| Validate robots.txt |
| Find broken links |
| Analyze heading structure |
| Check duplicate titles |
| Analyze keyword density |
# Install
npm install -g @seo-audit/remote-mcp
# Run the server
seo-audit-remote
# (Default: http://localhost:3456)curl -X POST http://localhost:3456/call \
-H "Content-Type: application/json" \
-d '{"name":"audit","arguments":{"url":"https://example.com"}}'MCP Clients (Claude Desktop, OpenCode, etc.)
│ │
stdio │ HTTP │
▼ ▼
┌──────────────┐ ┌──────────────────┐
│ local-mcp │ │ remote-mcp │
│ (stdio) │ │ (Express) │
└──────┬───────┘ └────────┬─────────┘
│ │
└──────────┬──────────┘
▼
┌──────────────┐
│ core │
│ (audit logic)│
└──────────────┘
│
▼
┌──────────────┐
│ cli │
│ (commander) │
└──────────────┘This is a Bun monorepo using workspaces.
# Prerequisites
curl -fsSL https://bun.sh/install | bash
# Install dependencies
bun install
# Build all packages
bun run build
# Run from source (no build needed)
bun run dev:cli # CLI
bun run dev:local # Local MCP
bun run dev:remote # Remote MCP
# Lint, format, typecheck
bun run lint
bun run format:check
bun run typecheckcd packages/<name>
npm publish --access publicRuntime: Bun / Node.js 20+
Language: TypeScript
Bundler: tsdown
Linting/Formatting: oxlint / oxfmt
MCP: @modelcontextprotocol/sdk
HTML Parsing: Cheerio
Validation: Zod
CLI: Commander
HTTP: Express (remote-mcp)
MIT
This server cannot be deployed
Free technical-SEO audit MCP: crawl a site, run checks, return an LLM-ready shareable report.
Your agent needs to crawl a site and say what is wrong with it — broken tags, duplicate content, pages nothing can index, resources that never load. **What you can ask for** • "Crawl this site and list every page with a duplicate title or missing description." • "Which pages are non-indexable, and why?" • "Run Lighthouse on these URLs and give me the failing audits." • "Show the internal link graph and the orphan pages." • "Give me this page's raw HTML and its microdata." **How to use it** Point any MCP client at https://mcp.aisa.one/seo-onpage/mcp and sign in with OAuth — there is no key to create or paste. 20 tools: submit a crawl and read its summary, pages, resources, links and waterfall; duplicate content and duplicate tags; keyword density; non-indexable and uncrawlable resources; parsed content, raw HTML, microdata, screenshots and Lighthouse. **Why this rather than the source** A crawler you drive from the agent, with the audit results as structured data rather than a PDF. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the broken pages here, then ask the same agent what those pages used to rank for — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo/mcp for all of it at once — rankings, keywords, backlinks, site health and AI-answer visibility across DataForSEO, Semrush and Ahrefs.
Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.
SEO Intelligence MCP — 13 tools: keyword research, SERP, domain audits, competitors.
