String Similarity Batch

String Similarity Batch MCP Connector for Claude

A+

High-performance string similarity computations for batch processing of large text arrays using algorithms like Levenshtein and Jaro-Winkler.

2 tools Official Updated Oct 1, 2026 Official Vinkius Partner

This MCP server provides precise, matrix-based string comparison metrics that are computationally expensive for LLMs. Use batch_rank_candidates to rank an array of strings against a target using metrics like levenshtein, jaro_winkler, or sorensen_dice. Alternatively, use compute_single_metric for one-to-one comparisons between two specific strings. It handles strings up to 5000 characters and supports algorithms including Damerau-Levenshtein and Longest Common Subsequence (LCS).

string-similaritylevenshteinbatch-processingfuzzy-matchingnlpalgorithms

2 tools expose this connector's capabilities to your AI agent.

compute_single_metric

for example Levenshtein) between two strings. Compute a string similarity metric

batch_rank_candidates

Rank candidates based on similarity to a target

See how to talk to your AI agent using String Similarity Batch.

Rank these names by Jaro-Winkler similarity to 'John': ['Jon', 'Johnny', 'James']

1. Jon (0.85), 2. Johnny (0.78), 3. James (0.62)

What is the Levenshtein distance between 'kitten' and 'sitting'?

The Levenshtein distance between 'kitten' and 'sitting' is 3.

Compare 'apple' and 'apply' using LCS.

The Longest Common Subsequence (LCS) length for 'apple' and 'apply' is 4.

Yes, the `batch_rank_canditates` tool is designed to process arrays of candidates efficiently.

Related Connectors