Score AI-likeness and remove Claude, ChatGPT and Gemini text watermarks.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional bearer token for removal beyond the free anonymous allowance.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Score a passage 0-100 for AI-likeness (stylometric heuristic). Free, no account.
The passage to score.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http zuro https://zuro.cc/mcp
Headers
Authorization (optional, not in the config above): Optional bearer token for removal beyond the free anonymous allowance.Score a passage 0-100 for AI-likeness (stylometric heuristic). Free, no account.
| Argument | Type | Description |
|---|---|---|
| text* | string |
| The passage to score. |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The passage to score."
}
}
}Remove the statistical AI-text watermark by re-generating every token. Returns clean text plus before/after scores.
| Argument | Type | Description |
|---|---|---|
| mode | string | |
| text* | string | The AI-generated passage to clean. |
{
"type": "object",
"required": [
"text"
],
"properties": {
"mode": {
"enum": [
"paraphrase",
"backtranslate"
],
"type": "string",
"default": "paraphrase"
},
"text": {
"type": "string",
"description": "The AI-generated passage to clean."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 16, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.