When should I use Levenshtein?

Levenshtein counts the absolute number of character edits (insertions, deletions, substitutions) required to match the strings. Great for simple spell-checks.

When is Jaro-Winkler better?

Jaro-Winkler gives a score from 0 to 1 and heavily weights matching prefixes. It is the industry standard for matching personal names in databases.

Why not use embeddings?

Embeddings match *meaning* (semantics). Fuzzy string distances match *characters* (lexical). If you want to match 'cat' to 'catt', string distance is better.

Fuzzy String Distance Engine MCP Connector for Claude

A+

Calculate exact Levenshtein, Jaro-Winkler, and Dice distances for fuzzy text matching natively local.

1 tools Official Updated Jun 28, 2026 Official Vinkius Partner

More Details Connect to Claude

When deduplicating lists of names or correcting misspellings (e.g. 'John Smith' vs 'Jon Smyth'), semantic embeddings are overkill and LLM prompting is unpredictable. This engine provides the academic gold-standard string distances: Levenshtein (edit distance), Jaro-Winkler (prefix-heavy similarity), and Dice coefficient. Computed strictly in local JS, it gives agents a mathematical foundation for entity resolution.

levenshteinstring-distancedata-cleaningtext-processingnormalization

Connect to Claude

Subscribe on Vinkius, then add this connector to Claude.ai or Claude Code.

① Claude.ai (web app)

Go to Settings → Connectors → Add custom connector
Paste the MCP endpoint URL below

https://edge.vinkius.com/vk_preview_xvVQOLDybWIA1r0Xqh3QvkWg4DBUiJY5auBfso8h/mcp

② Claude Code (terminal)

claude mcp add --transport http fuzzy-string-distance-engine https://edge.vinkius.com/vk_preview_xvVQOLDybWIA1r0Xqh3QvkWg4DBUiJY5auBfso8h/mcp

③ Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "fuzzy-string-distance-engine": {
      "url": "https://edge.vinkius.com/vk_preview_xvVQOLDybWIA1r0Xqh3QvkWg4DBUiJY5auBfso8h/mcp"
    }
  }
}

Get full access on Vinkius

The preview token above works for testing. Powered by Vinkius.