Levenshtein Distance Skill

Overview

Levenshtein Distance computes the classic edit distance between `string1` and `string2` with a full dynamic-programming matrix. Each cell holds the cheapest way to turn a prefix of one string into a prefix of the other, where an insertion, a deletion and a substitution each cost 1 and a matching character costs 0. `distance` is the value in the final cell. Transpositions are not a single operation, so "ab" to "ba" is a distance of 2, not 1.

The comparison is exact and character-by-character: it is case-sensitive, spaces and punctuation count, and characters are compared as JavaScript string units, so an emoji or other character outside the Basic Multilingual Plane counts as two. Lowercase or trim the strings yourself if you want "Apple" and "apple " to match.

`similarity` is (1 minus distance divided by the length of the longer string) times 100, rounded to two decimals. `matchLevel` is derived from that number: exactly 100 is `exact`, 80 or above `high`, 50 or above `medium`, 20 or above `low`, and anything lower `none`. Because similarity is normalized by length, one edit in a long string scores higher than one edit in a short one; use `distance` when you need an absolute threshold such as "at most two typos".

`string1Length` and `string2Length` are the lengths of the inputs as received, and `string1` and `string2` echo them back; these four fields are null on the Free plan. Computation time and memory grow with the product of the two lengths, so very long pairs take noticeably longer.

Live Test Levenshtein Distance Skill Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as LevenshteinDistanceSkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

{
  "name": "LevenshteinDistanceSkill",
  "arguments": {
    "string1": "kitten",
    "string2": "sitting"
  }
}

You do not name the tool yourself; the model picks it. Asking about kitten in the terms this skill covers is enough for it to reach for LevenshteinDistanceSkill on its own — naming it explicitly also works, and is the way to force the call.

Connecting

One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervekit": {
      "url": "https://api.vervekit.com/v1/mcp"
    }
  }
}

https://api.vervekit.com/v1/mcp

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

1
2
3
4
5
6
7
8
9
10
11
12
13

{
  "status": "ok",
  "error": null,
  "data": {
    "distance": 3,
    "similarity": 57.14,
    "matchLevel": "medium",
    "string1Length": 6,
    "string2Length": 7,
    "string1": "kitten",
    "string2": "sitting"
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

A call costs 1 credit each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

Spell Checking

Calculate similarity between misspelled words and dictionary entries

Fuzzy Search

Implement approximate string matching for search engines

Plagiarism Detection

Measure text similarity for detecting copied content

Data Deduplication

Identify near-duplicate records in databases

Other ways to use Levenshtein Distance Skill

Set up Levenshtein Distance Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.

Related

More in Text Processing: