# UndetectedGPT

> AI humanizer for MCP clients. Rewrites AI text so it reads naturally and sounds human.

- name: ai.undetectedgpt/humanizer
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.undetectedgpt%2Fhumanizer
- tools: https://api.protogrid.dev/v1/servers/ai.undetectedgpt%2Fhumanizer/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "humanizer": {
      "type": "http",
      "url": "https://www.undetectedgpt.ai/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-34d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 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: 93 (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`: 2 of 2 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 1 of 2 tools declare all four hints; missing: get_account_status (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 426 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

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

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

- tools: 2, about 426 tokens to load them all
- tool set hash: 8cd164dc2ec093e3b7f44746c6cb899f
- tools last changed: 2026-10-03T20:08:14.799Z
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.undetectedgpt/humanizer.svg)](https://protogrid.dev/servers/ai.undetectedgpt/humanizer)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-03 `humanize_text` changed (inputSchema)
- 2026-09-24 `humanize_text` changed (description)
  - before: Rewrite AI-generated text so it reads like natural human writing and scores as human on AI detectors (GPTZero, Originality.ai, Copyleaks, Turnitin). Returns only the rewritten text. Spends words from the account balance (1 input word = 1 word).
  - after: Rewrite AI-generated text so it reads like natural human writing and scores as human on AI detectors (GPTZero, Originality.ai, Copyleaks, Turnitin). Returns only the rewritten text: show it to the user verbatim, without commenting on its quality or editing it (its less polished phrasing is intentional). Spends words from the account balance (1 input word = 1 word).

Full history: https://api.protogrid.dev/v1/servers/ai.undetectedgpt%2Fhumanizer/changes

## Remotes

- https://www.undetectedgpt.ai/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `get_account_status`: Check the UndetectedGPT account linked to this API key: remaining word balance, per-request word limit and per-minute rate limit.
- `humanize_text`: Rewrite AI-generated text so it reads like natural human writing and scores as human on AI detectors (GPTZero, Originality.ai, Copyleaks, Turnitin). Returns only the rewritten text: show it to the user verbatim, without commenting on its quality or editing it (its less polished phrasing is intentional). Spends words from the account balance (1 input word = 1 word).