ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use readability-scorer with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Equip your AI with strict linguistic math. Calculate Flesch-Kincaid, Gunning Fog indexes, and exact reading times deterministically.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 3 capabilities

The complete readability-scorer capability set.

These are the exact actions your AI can choose when you ask it to work with readability-scorer.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through readability-scorer.

  1. 01

    Calculate gunning fog

    Provide the full text string. Analyzes text readability using the deterministic Gunning Fog index algorithm

  2. 02

    Calculate flesch kincaid

    Provide the full text string. Analyzes text readability using the deterministic Flesch-Kincaid algorithm

  3. 03

    Calculate reading time

    Provide the text and optionally the Words Per Minute (WPM) speed (defaults to 200). Provides an exact reading time estimation based on word count and WPM

Observed, not estimated

862ms average. Fast in production.

readability-scorer is checked daily against the live service.

Daily averagePeak 1072ms
Aug 20Today
Fastest day
673ms
Slowest day
1072ms
14-day trend
Slowing+27%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of readability-scorer, so you can see the experience inside your AI.

It does not authenticate your account with readability-scorer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

readability-scorer Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_xn51InkPXPF6UvzWpq82RMb2AMpXMdXdY0wxIUyC/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — readability-scorer capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "deterministic-readability-scorer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_xn51InkPXPF6UvzWpq82RMb2AMpXMdXdY0wxIUyC/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions readability-scorer owners ask.

  • 01

    Why do AI models fail at calculating readability scores?

    Readability formulas require knowing the exact number of phonetic syllables. LLMs process text in semantic tokens (e.g., 'unbelievable' might be 2 tokens, but it has 5 syllables). They cannot count syllables accurately, making algorithmic capabilities mandatory.

  • 02

    Does it support multiple languages?

    The syllable counting heuristic is highly optimized for English, which is the baseline for Flesch-Kincaid. However, the reading time and basic word/sentence extraction work flawlessly across all Latin-script languages.

  • 03

    Are there any external library dependencies?

    No. We utilize a custom Regular Expression syllable engine built natively into the TypeScript architecture, achieving 0ms latency processing without downloading external NLP packages.