# Ravixalgorithm Onto MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.ravixalgorithm%2Fonto
Registry id: `mcp-registry/io.github.ravixalgorithm/onto`
Status: auth-required (checked 2026-10-27T01:44:20.844Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 216
- Outages (90 days): 0

## Install

```json
{
  "mcpServers": {
    "ravixalgorithm-onto-mcp-server": {
      "type": "http",
      "url": "https://api.buildonto.dev/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http ravixalgorithm-onto-mcp-server https://api.buildonto.dev/mcp
```

## Tools (6)

- `batch`: Process many URLs in one call. N credits — one per URL in the list after the list is known. Failed URLs (ok: false) are refunded. Default mode read-and-score is
- `extract_data`: Return the structured data a page already declares — JSON-LD, OpenGraph, and meta tags — plus the AIO score. Deterministic; no fields are inferred by a model.
- `map_site`: Discover a site's URLs (sitemap → on-page links) without reading them. 1 credit per call (not per discovered URL) — use it to plan which pages to read or batch 
- `read_and_score`: Returns clean Markdown plus the AIO score in one call. Recommended default for agentic workflows.
- `read_url`: Returns clean Markdown for a URL with metadata about the extraction (sizes, reduction %, cache state).
- `score_url`: Returns the AIO (AI-readability) score for a URL — 0-100 with a letter grade, hallucination risk, and a structured list of penalties / benefits / recommendation

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.