Agentic SEO Check is one core with two interfaces:
- CLI
agentic-seo-check with a report for people on a terminal, JSON when piped, Markdown on request, and CI-friendly exit codes.
- MCP server exposing seven tools for Claude Code, Cursor, Codex and any other MCP client. A hosted server serves five of them, and a sixth for an agent's feedback, at
https://mcp.agentic-seo.rivi.software/mcp, free and without an install, for claude.ai, ChatGPT and any client that connects over HTTP. It is listed in the Claude Directory.
It audits URLs (production, staging, localhost dev servers), static build output (dist/, out/, build/) and raw HTML, and returns findings an agent can act on: a stable rule id, severity, what is wrong, the fix, a CSS selector for where it lives, and evidence with the current values. Each finding carries the exact edits that fix it, quoting the code to replace, and an id, so an agent can re-check only the rules it fixed and see which findings are gone, still open or new.
Two audits share that core: the SEO audit (audit, crawl) for search engines, and the AEO audit (aeo, answer engine optimization) for AI answer engines such as ChatGPT search, Claude, Perplexity, Google AI Overviews and AI Mode, Copilot and Gemini. Each has its own rules and its own score, so adding one never changes the other. A comparison (compare) puts a page beside competitors' pages and lists what they have that it lacks.
以上为 README 的开头部分。其余内容请阅读原文。 查看完整 README ↗
