# UndetectedGPT (remote · www.undetectedgpt.ai)

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

- Trust score: 80/100 (high trust)
- Change this week: +10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-03

## Components

- remote · `www.undetectedgpt.ai`: 80/100 (this document), [markdown](https://verifymcp.io/servers/ai-undetectedgpt-humanizer/api-mcp.md), [page](https://verifymcp.io/servers/ai-undetectedgpt-humanizer/api-mcp)

## Channel facts

- Endpoint: `https://www.undetectedgpt.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 463 tokens (~231/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the UndetectedGPT MCP server?

UndetectedGPT is a hosted endpoint at https://www.undetectedgpt.ai/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-undetectedgpt-humanizer 'https://www.undetectedgpt.ai/api/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.ai-undetectedgpt-humanizer]
url = "https://www.undetectedgpt.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-undetectedgpt-humanizer": {
      "type": "remote",
      "url": "https://www.undetectedgpt.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-undetectedgpt-humanizer --url 'https://www.undetectedgpt.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-undetectedgpt-humanizer:
    url: "https://www.undetectedgpt.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-undetectedgpt-humanizer": {
      "Transport": "http",
      "Url": "https://www.undetectedgpt.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-undetectedgpt-humanizer -t streamable-http -u 'https://www.undetectedgpt.ai/api/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-03 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-01 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-29 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 77, +7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-25 (score 69, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (2)

### `humanize_text` (~234 tokens)

Humanize AI 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).

Input parameters:

- `markdown` (boolean): Preserve markdown formatting in the output. Defaults to true.
- `model` (string): Humanizer model. Defaults to ghost-2 (latest).
- `spelling` (string): English spelling variant for the output. Defaults to us. English text only.
- `text` (string, required): The text to humanize. Minimum 5 words; maximum set by the API key (1000 words by default).
- `tone` (string): Writing tone. Omit, or use 'balanced' (equivalent), for the default style with no tone rewrite.
- `ultra_stealth` (boolean): Stronger restructuring for maximum detector evasion. Ignored when tone is conversational, formal or creative.

### `get_account_status` (~35 tokens)

Account status

Check the UndetectedGPT account linked to this API key: remaining word balance, per-request word limit and per-minute rate limit.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-undetectedgpt-humanizer/api-mcp#diagnostics

## Score history

- 2026-10-03: 80
- 2026-10-02: 79
- 2026-10-01: 79
- 2026-09-30: 78
- 2026-09-29: 78
- 2026-09-28: 77
- 2026-09-27: 70
- 2026-09-26: 70
- 2026-09-25: 69
- 2026-09-24: 70
- 2026-09-23: 69
- 2026-09-22: 69
- 2026-09-21: 68
- 2026-09-20: 68
- 2026-09-19: 67
- 2026-09-18: 67
- 2026-09-17: 67
- 2026-09-16: 66
- 2026-09-15: 66

## Common questions

### What is the UndetectedGPT MCP server?

UndetectedGPT is an MCP server listed in the public MCP registry as ai.undetectedgpt/humanizer. AI humanizer for MCP clients. Rewrites AI text so it reads naturally and sounds human. This page covers its hosted endpoint (https://www.undetectedgpt.ai/api/mcp).

### Is the UndetectedGPT MCP server safe to use?

UndetectedGPT scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the UndetectedGPT MCP server expose?

UndetectedGPT exposes 2 tools: humanize_text, get_account_status. Their descriptions and schemas cost roughly 269 tokens of context every time the server is loaded.

### Does the UndetectedGPT MCP server require authentication?

No. We connected to UndetectedGPT without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the UndetectedGPT MCP server still maintained?

UndetectedGPT is still listed as active in the MCP registry. We last reached this channel on 3 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://www.undetectedgpt.ai/api/mcp
- Website: https://www.undetectedgpt.ai/feature/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-undetectedgpt-humanizer/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-undetectedgpt-humanizer/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-undetectedgpt-humanizer/api-mcp