Skip to main content
Glama

Server Details

Score AI-likeness and remove Claude, ChatGPT and Gemini text watermarks.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 2 tools

Disambiguation5/5

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.

Naming Consistency5/5

Both names follow the same snake_case verb_noun pattern (check_/remove_), and the verbs accurately reflect the operations. No stylistic mixing.

Tool Count3/5

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.

Completeness4/5

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 tools
check_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

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables 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.
      3
      MIT
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables 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.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables 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
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources