Local-first MCP server for auditing a public website’s AI visibility and crawler readiness. It checks signals such as llms.txt, robots.txt, sitemap, canonical, metadata, noindex, and JSON-LD, and returns a local-only visibility report and action plan.
From the registry: Local-first MCP server for AI visibility, GEO/AEO, llms.txt, and AI crawler readiness audits.
Please install the `maxaeo-ai-visibility-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js and npm** — Node.js and npm are required to run the MCP server via npx or install it globally from npm.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","maxaeo-ai-visibility-mcp"]
- optional environment variables:
- `MAXAEO_LOCALE`: Default output locale when not provided in the tool call. Supported examples include en-US, en, global, zh-CN, zh, cn. (example: `<locale>`)
- `MAXAEO_MARKET`: Default CTA market when not provided in the tool call. Supported values include global and cn. (example: `<market>`)
- `MAXAEO_CTA_URL_CN`: Optional custom MaxAEO CTA landing page URL for the China market. (example: `<your-cn-cta-url>`)
- `MAXAEO_CTA_URL_GLOBAL`: Optional custom MaxAEO CTA landing page URL for the global market. (example: `<your-global-cta-url>`)
Note: The README shows both global npm install and npx usage; the simplest portable MCP config is to run the server with npx. No API key is required for the default local-first functionality.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MAXAEO_LOCALESets the default output locale for tool calls.MAXAEO_MARKETSets the default CTA market (global or cn).MAXAEO_CTA_URL_CNCustom CTA landing page for the China market.MAXAEO_CTA_URL_GLOBALCustom CTA landing page for the global market.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.