Why can't my AI just calculate these distances itself?

LLMs are probabilistic and tend to approximate math. This leads to errors in high-dimensional spaces where precision is required.

Does this MCP work with OpenAI embeddings?

Yes, it is designed to handle 1536-dimensional vectors commonly used in those embeddings.

Is my data safe when using this capability?

Yes, the math is performed locally, so your embedding vectors and model weights do not leave your machine.

Which distance metrics are supported?

The MCP supports Cosine, Euclidean, Manhattan, and Chebyshev distances.

Which AI clients can use this MCP?

You can use this with any MCP-compatible client like Claude, Cursor, Windsurf, or VS Code.

Is Cosine distance the same as Cosine similarity?

No, Cosine Distance equals 1 minus Cosine Similarity. The engine returns both exact values in the JSON response so you always have the complete picture.

Can it compare 1536-dimensional embeddings like OpenAI's?

Yes! It processes any equal-length array instantly. 1536-dimensional vectors are evaluated in milliseconds local, with exact floating-point precision.

What if the two vectors have different lengths?

The engine enforces a strict validation constraint and throws a clear error. Both arrays must be mathematically equal in length. there is no silent truncation or padding.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Distance Metrics Engine to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get mathematically perfect similarity scores without hallucinations.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 1 capability

We ship only the actions that matter.

Capability set01 / 01

01

1 capability in this set.

Part of 1 available through Distance Metrics Engine.

01
Calculate distance
This capability computes exact Cosine, Euclidean, or Manhattan distances between high-dimensional vectors. It runs entirely offline to ensure your embeddings stay private and your results are mathematically sound.

Real work

What teams actually run

RAG Accuracy

Use exact Cosine similarity to find the most relevant document chunks for a retrieval-augmented generation pipeline.

Anomaly Detection

Calculate Euclidean distance to identify data points that sit far from a known cluster centroid.

Clustering Validation

Verify the tightness of clusters by measuring Manhattan distances between points and their assigned centers.

Embedding Comparison

Compare different embedding models by calculating the distance between their outputs for the same text.

Automate a task

Put Distance Metrics Engine to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Distance Metrics Engine works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Distance Metrics Engine to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

876ms average. Fast in production.

Distance Metrics Engine is checked daily against the live service.

Daily averagePeak 1110ms

Oct 3Today

Fastest day: 653ms
Slowest day: 1110ms
14-day trend: Improving-17%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 1 capability arrives ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Distance Metrics Engine, so you can see the experience inside your AI.

It does not authenticate your account with Distance Metrics Engine. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Distance Metrics Engine Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://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.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "distance-metrics-engine-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_y2uLWGNkX2DGyvuukg2OciAQezxFmCM92SNAHYKa/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Distance Metrics Engine in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Distance Metrics Engine owners hand off.

This MCP is built for developers and data scientists who need to bridge the gap between probabilistic AI and deterministic math.

01
Machine Learning Engineer
Hands off vector similarity tasks to the MCP to ensure model evaluation is accurate.
02
AI Application Developer
Uses the capability to build RAG systems that require precise document retrieval.
03
Data Scientist
Delegates high-dimensional distance calculations to the agent for rapid prototyping.

FAQ

Questions Distance Metrics Engine owners ask.

01
Why can't my AI just calculate these distances itself?
LLMs are probabilistic and tend to approximate math. This leads to errors in high-dimensional spaces where precision is required.
02
Does this MCP work with OpenAI embeddings?
Yes, it is designed to handle 1536-dimensional vectors commonly used in those embeddings.
03
Is my data safe when using this capability?
Yes, the math is performed locally, so your embedding vectors and model weights do not leave your machine.
04
Which distance metrics are supported?
The MCP supports Cosine, Euclidean, Manhattan, and Chebyshev distances.
05
Which AI clients can use this MCP?
You can use this with any MCP-compatible client like Claude, Cursor, Windsurf, or VS Code.
06
Is Cosine distance the same as Cosine similarity?
No, Cosine Distance equals 1 minus Cosine Similarity. The engine returns both exact values in the JSON response so you always have the complete picture.
07
Can it compare 1536-dimensional embeddings like OpenAI's?
Yes! It processes any equal-length array instantly. 1536-dimensional vectors are evaluated in milliseconds local, with exact floating-point precision.
08
What if the two vectors have different lengths?
The engine enforces a strict validation constraint and throws a clear error. Both arrays must be mathematically equal in length. there is no silent truncation or padding.

Explore

More in Developer Tools

Connect Distance Metrics Engine to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01

Calculate distance

What teams actually run

RAG Accuracy

Anomaly Detection

Clustering Validation

Embedding Comparison

Building your own app? The connector is yours to use.

Distance Metrics Engine Connector

Claude Desktop

Machine Learning Engineer

AI Application Developer

Data Scientist

Why can't my AI just calculate these distances itself?

Does this MCP work with OpenAI embeddings?

Is my data safe when using this capability?

Which distance metrics are supported?

Which AI clients can use this MCP?

Is Cosine distance the same as Cosine similarity?

Can it compare 1536-dimensional embeddings like OpenAI's?

What if the two vectors have different lengths?

Oracle Vector DB AI Connector

DataFrame Aggregator Engine AI Connector

One-Hot Encoder Engine AI Connector

Milvus (Open-Source Vector Database) AI Connector

Suggestions

Embedding Similarity Calculator AI Connector

Vector Similarity Threshold Enforcer AI Connector

Data Pipeline Prover AI Connector

pgvector (Vector Database) AI Connector