Zuro
Server Details
Score AI-likeness and remove Claude, ChatGPT and Gemini text watermarks.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
check_score (detection) and remove_watermark (transformation) target clearly different actions on the same input, and the descriptions make the boundary obvious. An agent can choose correctly without hesitation.
Both names follow the same snake_case verb_noun pattern (check_/remove_), and the verbs accurately reflect the operations. No stylistic mixing.
Two tools is thin for a server surface, even a focused one, and leaves no room for adjacent operations like batch scoring or text input helpers. It is defensible given the narrow detect-and-remove purpose, but sits at the borderline the rubric describes.
The core lifecycle is closed: score a passage, then remove the watermark with before/after scores returned for verification. Minor gaps exist (no batch processing, no score breakdown or history), but agents can complete the primary workflow without dead ends.
Available Tools
2 toolscheck_scoreBInspect
Score a passage 0-100 for AI-likeness (stylometric heuristic). Free, no account.
Inputs: text (required).
remove_watermarkBInspect
Remove the statistical AI-text watermark by re-generating every token. Returns clean text plus before/after scores.
Inputs: text (required), mode.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Scores whether a page reads as AI-generated and names the tells to fix.
Score text 0-100 for signs of AI writing, with plain reasons; strip machine typography.
Score and rewrite AI-assisted prose while preserving names, numbers, quotes, links, and facts.
Find AI-isms with evidence and fingerprint a writing voice from samples. 3 of 5 free.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables users to check AI-assisted drafts for writing-pattern findings, locally clean selected hidden Unicode and lookalike characters, and optionally request API-key-authorized rewrites.3MIT
- AlicenseAqualityBmaintenanceFinds and removes AI writing tells with a deterministic ruleset. Runs locally by default; an optional pass can call a model if you turn it on.45MIT
- FlicenseNot gradedqualityAmaintenanceEnables agents and users to analyze text or files for formulaic AI writing patterns and receive a 0–100 score, band label, violations with surrounding context, and concrete advice. It works programmatically without LLM judges or API calls.-
- AlicenseNot gradedqualityCmaintenanceEnables agents to strip AI-writing tells from model output by humanizing raw text or files and scoring how much AI flavor remains, using three tools. All filtering happens on the output side, so prompts, token usage, and prefix-cache hits stay untouched.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.