- PRECISION
- VALIDATION
- RANKING
- HUMAN
Short answer
How can I get exact vector similarity scores?
Your AI uses the calculate_distance tool to run specific mathematical formulas against your embedding vectors. This provides precise numerical values instead of text-based approximations. You'll get specific distance scores for any vectors you provide.
The results you get
Mathematical outcomes
The AI handles the heavy math and gives you the final numbers.
PRECISION
Exact distance scores
The AI returns specific numerical values. You get the actual distance between vectors rather than a vague description.
VALIDATION
Embedding audits
Check how well your vectors cluster or separate. The AI provides the metrics needed to inspect your vector space.
RANKING
Top match identification
Use the calculated scores to sort results. Your AI can rank vectors to find the closest neighbors in a set.
HUMAN
Threshold decisions
The AI provides the math, but you decide if the similarity score meets your specific requirements.
The workflow
What your AI does when you provide vectors.
The AI acts as the bridge between your prompt and the math engine.
Receive vectors
Your AI takes the high-dimensional arrays or embedding lists you paste into the chat.
calculate_distanceSelect metric
The AI picks the right formula, like Cosine or Euclidean distance, based on what you ask for.
calculate_distanceExecute math
The engine runs the calculation to find the exact distance between the points.
calculate_distanceReport results
The AI gives you the final numerical distance score.
calculate_distance
Try it
Copy these to start.
Use these prompts to trigger the math immediately.
Starting points
Swap the bracketed numbers for your actual embedding vectors.
Distance Metrics Engine Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_y2uLWGNkX2DGyvuukg2OciAQezxFmCM92SNAHYKa/mcp
Claude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Distance Metrics Engine capabilities are ready to use.
{
"mcpServers": {
"distance-metrics-engine-mcp": {
"url": "https://edge.vinkius.com/vk_preview_y2uLWGNkX2DGyvuukg2OciAQezxFmCM92SNAHYKa/mcp"
}
}
}Calculate the cosine similarity between these two vectors: [0.1, 0.2, 0.3] and [0.1, 0.2, 0.4].
Find the Euclidean distance between the embedding in my CSV and this vector: [0.5, 0.5, 0.5].
Compare the similarity of these three vectors from my research file and tell me which two are closest.
Use the distance engine to check how far these two high-dimensional embeddings are from each other.
- Claude
ChatGPT
Cursor
VS Code
Windsurf- Claude Code
JetBrains
Cline
Start here
Connect Distance Metrics Engine once, then ask.
One click connects this MCP to your client. Your credentials stay encrypted and your data stays private.
Connect Distance Metrics Engine to your AIFAQ
How the distance engine behaves
- 01
Does the AI guess the similarity?
No. The AI uses the calculate_distance tool to perform exact math instead of using its own reasoning.
- 02
Can the AI change my original vectors?
No. The tool only reads the vectors you provide to perform calculations; it cannot modify your data.
- 03
What metrics can it use?
It can perform various mathematical distance calculations, such as Cosine similarity or Euclidean distance, depending on your request.
- 04
Can the AI store these vectors for me?
No. This MCP is for calculation only. It does not act as a vector database.
- 05
Do I need to provide the vectors manually?
Yes. You must provide the vectors in the chat or point the AI to the data source you want it to process.
More questions about Distance Metrics Engine? The Connector page answers them. See everything the Distance Metrics Engine Connector can do
Connect Distance Metrics Engine to Claude, Cursor, ChatGPT & more