# Cryptosun Proximens Oracle MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.cryptosun%2Fproximens-oracle
Registry id: `mcp-registry/io.github.cryptosun/proximens-oracle`
Status: live (checked 2026-10-26T18:09:42.481Z)

## Verdict

Cryptosun Proximens Oracle MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1180 ms median handshake and 2 outages in 90 days. Its agent-readiness grade is A (95/100) across 8 tools, costing an agent about 2,122 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 1180 ms | 17% of MCP servers |
| p95 handshake latency | 2586 ms | — |
| Checks in 30 days | 4,893 | — |
| Outages, 90 days | 2 | — |
| Median recovery | 7 min | — |
| Agent-readiness score | 95/100 (A) | 80% of MCP servers |
| Tools | 8 | — |
| Tool-list size for an agent | ~2,122 tokens | 51% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "cryptosun-proximens-oracle-mcp-server": {
      "type": "http",
      "url": "https://www.proximens.nl/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http cryptosun-proximens-oracle-mcp-server https://www.proximens.nl/mcp
```

## Tools (8)

- `proximens_geo_audit_url`: Pro-tier. Fetch and analyze a web page, then audit it against the Proximens GEO Engine principles across all major GEO dimensions (structured data, crawler acce
- `proximens_geo_bulk_search`: Pro-tier. Run many GEO-principle searches in a single fast call. INPUT: queries (array of 2-100 natural-language strings, each 3-500 chars); optional top_k_per_
- `proximens_geo_compare_urls`: Pro-tier. Fetch two web pages (your URL and a competitor's) and audit both against the Proximens GEO Engine principles using the same audit engine as audit_url,
- `proximens_geo_get_principle`: Fetch one GEO principle from the Proximens GEO Engine by its UUID. INPUT: id (UUID, normally taken from a prior search_principles result). RETURNS: a single pri
- `proximens_geo_get_stats`: Return live aggregate statistics for the Proximens GEO Engine knowledge base. INPUT: none. RETURNS: JSON with total_principles (high-confidence count), total_ca
- `proximens_geo_list_categories`: List the GEO principle taxonomy of the Proximens GEO Engine with a live count of high-confidence principles per category. INPUT: none. RETURNS: JSON with a cate
- `proximens_geo_search_principles`: Semantic search over the Proximens GEO Engine: a curated, continuously-updated knowledge base of 4.000+ verified Generative Engine Optimization (GEO/AEO) princi
- `proximens_geo_synthesize_brief`: Generate a structured, GEO-optimized content brief for a topic using the Proximens GEO Engine. INPUT: topic (3-200 chars); optional target_branche (one of 7 ver

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