# AI Text Checker by carrierscan

> Check if AI wrote a text: English, Ukrainian, Kazakh, Uzbek, Estonian, Georgian, Lithuanian.

- name: app.carrierscan/ai-text-checker
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 81/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/app.carrierscan%2Fai-text-checker
- tools: https://api.protogrid.dev/v1/servers/app.carrierscan%2Fai-text-checker/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ai-text-checker": {
      "type": "http",
      "url": "https://carrierscan.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-2d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 1 of 1 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_ai_text (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 167 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 2 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 1, about 167 tokens to load them all
- tool set hash: a0f4787ffb0111ab093c4597a9e64b4e
- tools last changed: 2026-10-18T17:18:42.088Z
- badge: [![protogrid quality](https://protogrid.dev/badge/app.carrierscan/ai-text-checker.svg)](https://protogrid.dev/servers/app.carrierscan/ai-text-checker)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-18 `check_ai_text` changed (description, inputSchema)
  - before: Checks whether English or Ukrainian text (50-2,000 words) looks AI-written. Ukrainian text goes to our own Ukrainian detector (one detector). English text goes to the Desklib detector (DeBERTa-v3 classifier, gives an AI likelihood for the whole text and for ~500-word sections). Detectors make mistakes; never present the result as proof. Text is not stored.
  - after: Checks whether a text (50-2,000 words) looks AI-written, for example by ChatGPT, Gemini or Claude. Languages: English, Ukrainian, Kazakh, Uzbek, Estonian, Georgian, Lithuanian. Each language other than English is checked by our own detector trained on that language. Returns an AI likelihood for the whole text and for each part. Detectors make mistakes; never present the result as proof. Text is not stored.

Full history: https://api.protogrid.dev/v1/servers/app.carrierscan%2Fai-text-checker/changes

## Remotes

- https://carrierscan.app/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (1)

- `check_ai_text`: Checks whether a text (50-2,000 words) looks AI-written, for example by ChatGPT, Gemini or Claude. Languages: English, Ukrainian, Kazakh, Uzbek, Estonian, Georgian, Lithuanian. Each language other than English is checked by our own detector trained on that language. Returns an AI likelihood for the whole text and for each part. Detectors make mistakes; never present the result as proof. Text is not stored.