# `io.github.kwizzlesurp10-ctrl/apexseo-geo-mcp` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/io.github.kwizzlesurp10-ctrl/apexseo-geo-mcp
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.kwizzlesurp10-ctrl/apexseo-geo-mcp
- Version: 0.1.1 (active)
- Publisher: io.github.kwizzlesurp10-ctrl (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/kwizzlesurp10-ctrl/apexseo-geo-mcp
- Metadata from the official MCP Registry, synced 2026-11-20T12:17:38.377Z

Title and description, as the publisher wrote them:

```untrusted-server-text
ApexSEO GEO & AI-Crawler Audit MCP
Keyless Base USDC x402 MCP for live AI-crawler, GEO/AEO & JSON-LD citation audits.
```

Scanned 2026-11-20T12:18:21.238Z over streamable-http.

**6 tools: 6 change things.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 6 | ask |
| Only reads | read | 0 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__apexseo-geo__ai_crawler_audit` `mcp__apexseo-geo__geo_competitor_compare` `mcp__apexseo-geo__geo_page_audit` `mcp__apexseo-geo__schema_citation_check` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__apexseo-geo__ai_crawler_audit` `mcp__apexseo-geo__geo_competitor_compare` `mcp__apexseo-geo__geo_page_audit` `mcp__apexseo-geo__schema_citation_check` |

## Findings

- **warn** Annotations that disagree with the tool in `geo_competitor_compare` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "geo_competitor_compare" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "geo_competitor_compare" says "compare": a word for reading.
```


## Changes things (6)

Creates or changes something that can be changed back. Claude Code: ask.

### `ai_crawler_audit`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Live-fetches a domain's /robots.txt, /llms.txt, /llms-full.txt, /sitemap.xml, and /.well-known/{x402,mcp,agent-card.json} files, returning a per-bot permission matrix (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, PerplexityBot, Google-Extended, Bingbot, Applebot-Extended, CCBot), AI-crawler readiness score (0-100), and ICE fixes. Use geo_page_audit for HTML/TTFB signals or schema_citation_check for JSON-LD validation.
```

### `geo_competitor_compare`

- The name "geo_competitor_compare" says "compare": a word for reading.
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "run" and "url": it reads web pages, which anyone can write. The input takes a URL (input.targetUrl), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.targetUrl): a request to a URL can carry data to whoever runs it.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Runs parallel live page GEO audits and AI-crawler (robots.txt / llms.txt) checks across your targetUrl and 1-3 competitorUrls, computing exact win/loss deltas across geoScore, AI-crawler readiness, TTFB speed, schema depth, question headings, and llms.txt coverage, plus a ranked ICE counter-strategy roadmap.
```

### `geo_health`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Free diagnostic check returning live service uptime, supported AI crawler matrix, x402 payment configuration (Base USDC payTo and CDP facilitator readiness), and SSRF protection status. Call this or geo_pricing first before running paid live-site audits.
```

### `geo_page_audit`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Performs a comprehensive live technical + Generative Engine Optimization (GEO/AEO) audit of any URL: measures TTFB, redirect chain, X-Robots-Tag, meta robots, canonical/hreflang, compression & security headers, title/meta/OpenGraph, H1-H3 question-heading density, structured lists/tables, empty CSR-shell detection, image alt coverage, E-E-A-T trust signals, composite geoScore (0-100), and ApexSEO Elite ICE action plan. Pair with ai_crawler_audit for site-wide robots.txt/llms.txt or geo_competitor_compare for rival benchmarking.
```

### `geo_pricing`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Free pricing manifest listing all ApexSEO GEO audit endpoints, Base Mainnet (eip155:8453) USDC prices ($0.01-$0.05), endpoint paths, and MCP Streamable HTTP connection details. Ideal sibling to geo_health before dispatching paid calls.
```

### `schema_citation_check`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Extracts and validates all embedded application/ld+json blocks (including @graph trees) on a live page, flags syntax errors and missing AI-citation properties for Organization, WebSite, SoftwareApplication, Product, Article, FAQPage, and WebPage entities, scores schema completeness (0-100), and outputs a ready-to-paste JSON-LD @graph patch customized from detected metadata.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `apexseo-geo`:

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__apexseo-geo__geo_health",
      "mcp__apexseo-geo__geo_pricing",
      "mcp__apexseo-geo__ai_crawler_audit",
      "mcp__apexseo-geo__geo_page_audit",
      "mcp__apexseo-geo__schema_citation_check",
      "mcp__apexseo-geo__geo_competitor_compare"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__apexseo-geo__ai_crawler_audit`: untrusted-input, outbound
- `mcp__apexseo-geo__geo_page_audit`: untrusted-input, outbound
- `mcp__apexseo-geo__schema_citation_check`: untrusted-input, outbound
- `mcp__apexseo-geo__geo_competitor_compare`: untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:20:07.510Z, unchanged since 2026-11-20T18:20:07.510Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `6` |
| Protocol version | `2025-03-26` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.

https://apexseo-geo-mcp.vercel.app/mcp: tools/list returned 6 tools to an anonymous client, including geo_health (write), geo_pricing (write), ai_crawler_audit (write), geo_page_audit (write), schema_citation_check (write) and 1 more
```
