What metrics are supported?

The calculator supports Cosine Similarity, Euclidean Distance, Dot Product Similarity, and Manhattan Distance. Tools available: `your_tool_name`.

Do all vectors need to have the same size?

Yes, for any mathematical comparison to be valid, all vectors involved must share the exact same dimensionality.

How does ranking work for distance metrics?

For distance-based metrics like Euclidean and Manhattan, vectors with smaller values are ranked higher. For similarity-based metrics like Cosine and Dot Product, larger values are ranked higher.

Embedding Similarity Calculator MCP Connector for Claude

Calculate mathematical distances and similarity scores between multidimensional numerical vectors.

0 tools Official Updated Oct 1, 2026 Official Vinkius Partner

More Details Connect to Claude

The Embedding Similarity Calculator provides precise mathematical computations for comparing multidimensional vectors. Using tools like compute_pairwise_metrics, you can determine cosine similarity, Euclidean distance, dot product, and Manhattan distance between pairs. The rank_vectors_by_metric tool allows you to search through large sets of candidate vectors by finding the most similar or closest entries based on your chosen metric. Additionally, validate_vector_dimensions ensures that all vectors in a collection are mathematically compatible for group operations.

Available Tools

your_tool_name

vectorscosine-similarityeuclidean-distancedot-productmanhattan-distanceembeddings

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_Jw1zV0EdxZijh9ns0Ve4DwNFVTYvTKlOlQyDwkeV/mcp

② Claude Code (terminal)

claude mcp add --transport http embedding-similarity-calculator https://edge.vinkius.com/vk_preview_Jw1zV0EdxZijh9ns0Ve4DwNFVTYvTKlOlQyDwkeV/mcp

③ Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "embedding-similarity-calculator": {
      "url": "https://edge.vinkius.com/vk_preview_Jw1zV0EdxZijh9ns0Ve4DwNFVTYvTKlOlQyDwkeV/mcp"
    }
  }
}

Get full access on Vinkius

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