Skip to main content
Glama
peopleworks

signs-of-ai

by peopleworks
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Related Servers

Alternatives to signs-of-ai

No user-submitted related servers found.

    Related Servers

    • avoid-ai-writing-mcp

      conorbronsdon
      A
      license
      A
      quality
      A
      maintenance
      Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.
      2
      2 npm
      3
      MIT

    • mcp-ai-detection

      carminelau
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables multi-tier AI-detection screening on academic papers by extracting text from .tex and .docx files, splitting into standard sections, and running a pipeline of statistical and LLM-based analysis.
      MIT

    • slop-guard

      YannisGreen055
      F
      license
      Not graded
      quality
      A
      maintenance
      Analyzes text and files for formulaic AI writing patterns, returning a 0-100 score, band label, specific violations with context, and concrete revision advice. Runs entirely locally with rule-based heuristics, requiring no LLM judge or API calls.
      -

    • AI Text Detection with

      houtini-ai
      A
      license
      Not graded
      quality
      C
      maintenance
      ai-detect is a free AI text detector that runs entirely on your own hardware. It scores writing sentence by sentence using desklib/ai-text-detector-v1.01, a 304-million-parameter DeBERTa-v3-large model that ranks first on the RAID detection benchmark. No API key, no per-word pricing and no upload: after a one-off 1.7 GB model download it just works offline. by Houtini
      10
      MIT

    • slop-guard

      taichiwilson161
      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.
      -
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.4/5.0

    Scored across 10 tools

    Disambiguation4/5

    Each tool targets a distinct analysis vector—stylometry, perplexity, hidden characters, citation consistency, exact copying, paraphrased copying, authorship baseline, and report generation—so most are easy to distinguish. The main ambiguity is between check_originality and check_paraphrase, and secondarily among analyze_ai_writing, measure_predictability, and write_report as related ways of assessing AI-like writing.

    Naming Consistency5/5

    All tool names follow a consistent imperative verb + object pattern in snake_case, such as search_catalog, check_citations, and write_report. The only minor deviation is compare_to_baseline with its preposition, but it still fits the overall pattern clearly.

    Tool Count5/5

    Ten tools cover a broad but coherent scope for an AI-writing analysis server: core analysis, predictability, authorship baseline, plagiarism and paraphrase checks, character inspection, citation validation, a reference catalog, and report generation. Each tool earns its place and none feel redundant.

    Completeness5/5

    The tool surface covers the full workflow of a document review for AI-writing signs: analyze stylistic signals, measure predictability, check for copying and paraphrasing, inspect hidden characters, validate citations, extract distinctive phrases for further checking, and produce a final report. Live web search and whole-internet plagiarism indexing are explicitly out of scope by design.

    Maintenance

    ActivitySlowing
    ResponsivenessWithin a week

    Resources