An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Retrieval Relevance Scorer 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. Stop feeding your AI irrelevant context and noise.

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.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

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.

A futuristic MCP client docking bay
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 · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Retrieval Relevance Scorer.

  1. 01

    Analyze coverage gap

    This capability finds exactly which query terms are missing from your current document set. It helps you see why your retrieval might be failing to provide the right context.

  2. 02

    Get scoring config

    This capability pulls the current weight distributions and scoring parameters. Use it to see how the engine is prioritizing different metrics.

  3. 03

    Score documents

    This capability calculates relevance scores for a group of documents against a specific query. It's the primary way to filter out low-quality context.

Real work

What teams actually run

01

RAG Optimization

Filter out documents that have high vector similarity but low actual keyword relevance.

02

Debugging Retrieval

Find out why an agent is missing facts by checking for coverage gaps in the retrieved data.

03

Context Window Management

Ensure only the most important documents occupy the limited space in your AI client's prompt.

04

Quality Assurance

Use deterministic scores to audit the performance of a search engine or database.

One connector, every AI

Retrieval Relevance Scorer 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.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

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

You don't need a client to put Retrieval Relevance Scorer 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

870ms average. Fast in production.

Retrieval Relevance Scorer is checked daily against the live service.

Daily averagePeak 936ms
Oct 14Today
Fastest day
753ms
Slowest day
936ms
14-day trend
Slowing+24%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive 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 Retrieval Relevance Scorer, so you can see the experience inside your AI.

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

Retrieval Relevance Scorer Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Retrieval Relevance Scorer capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "retrieval-relevance-scorer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/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 Retrieval Relevance Scorer in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Retrieval Relevance Scorer owners hand off.

This MCP is built for engineers and researchers working with RAG-based systems who need to move past basic vector search.

  • 01

    AI Engineers

    They hand off raw retrieval sets to the MCP to clean up context before prompting.

  • 02

    Data Scientists

    They use the scoring metrics to evaluate the quality of their retrieval pipelines.

  • 03

    LLM Developers

    They use it to reduce hallucinations in agentic workflows.

FAQ

Questions Retrieval Relevance Scorer owners ask.

  • 01

    How does this MCP reduce hallucinations?

    It prevents the AI from seeing irrelevant or noisy text that might confuse its reasoning. By filtering documents using deterministic math, only high-signal context reaches the prompt.

  • 02

    What metrics does the scoring engine use?

    The engine uses Jaccard Similarity for keyword overlap, TF-IDF Cosine Similarity for term importance, and Query Term Coverage for information density.

  • 03

    Can I see how the scores are calculated?

    Yes, you can use the get_scoring_config capability to inspect the current weight distributions and operational parameters.

  • 04

    Which AI clients can use this MCP?

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

  • 05

    How do I find out if my documents are missing information?

    Use the analyze_coverage_gap capability to identify which specific terms from your query are not present in the document set.

  • 06

    How does the scoring work?

    The engine calculates a composite score by combining Jaccard similarity, TF-IDF cosine similarity, and query term coverage using configurable weights.

  • 07

    Can I customize the weights?

    Yes, you can pass a custom weights object to the score_documents capability to prioritize different metrics like keyword overlap or TF-IDF.

  • 08

    How do I diagnose why a document was filtered out?

    You can use the analyze_coverage_gap capability to identify which specific terms from your query are missing from the retrieved documents.

Explore

More in Data Processing

Suggestions

Connect Retrieval Relevance Scorer to Claude, Cursor, ChatGPT & more