Retrieval Relevance Scorer Connector for AI agents.
3 live capabilities
Clean up RAG pipelines with deterministic scoring
Waiting for input…
Why people use Retrieval Relevance Scorer
Stop RAG hallucinations with Retrieval Relevance Scorer
This MCP changes the workflow. Instead of hoping for the best, you add a mathematical checkpoint. You pass your retrieved chunks through a scoring engine that checks for actual term importance and coverage. You end up with a clean, high-signal context window that actually contains the answers, making your agent much more reliable.
What Vinkius changes
That it replaces fuzzy similarity with deterministic math to stop hallucinations.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Fixing Hallucinations in Customer Support
A support agent keeps giving wrong answers because the vector search pulls in outdated manuals.
- Real-world use case 02
Optimizing Legal Document Search
An attorney needs to find specific clauses.
- Real-world use case 03
Debugging RAG Performance
A developer notices an agent can't answer questions about 'photosynthesis'.
Complete set · 3capabilities
The complete Retrieval Relevance Scorer capability set.
These are the exact actions your AI can choose when you ask it to work with Retrieval Relevance Scorer.
01—03
3 capabilities in this set.
Part of 3 available through Retrieval Relevance Scorer.
- 01 Capability
Get scoring config
Shows the current mathematical weights used for scoring. Use this to tune how much importance is placed on keyword overlap versus term importance.
- 02 Capability
Analyze coverage gap
Finds which specific query terms are missing from your documents. This helps you understand why an agent might be failing to answer a question.
- 03 Capability
Score documents
Calculates a relevance score for a list of documents against a query. It's the primary way to rank and filter your context.
Set up in minutes
One URL. Then ask Retrieval Relevance Scorer to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Retrieval Relevance Scorer from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Retrieval Relevance Scorer, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Retrieval Relevance Scorer for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Retrieval Relevance Scorer URL.
- Step 03
Save and start
Save the connection and enable Retrieval Relevance Scorer in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"retrieval-relevance-scorer": {
"url": "https://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Retrieval Relevance Scorer
Open Agent mode in chat and ask: "Using Retrieval Relevance Scorer, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"retrieval-relevance-scorer": {
"url": "https://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Retrieval Relevance Scorer
Ask Copilot: "Using Retrieval Relevance Scorer, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"retrieval-relevance-scorer": {
"url": "https://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Retrieval Relevance Scorer
Open Cascade and ask: "Using Retrieval Relevance Scorer, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"retrieval-relevance-scorer": {
"url": "https://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Retrieval Relevance Scorer
Ask Cline: "Using Retrieval Relevance Scorer, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add retrieval-relevance-scorer --transport http "https://edge.vinkius.com/vk_preview_Kx7cXouaqZrfTsnawEqwgyW4QrEjd9p5Y4I1xFB8/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Retrieval Relevance Scorer
Ask Claude: "Using Retrieval Relevance Scorer, show me...". 3 tools are ready
Where the request belongs
Work Retrieval Relevance Scorer can move forward.
This is for engineers and data scientists building RAG applications who are tired of their agents hallucinating due to poor context quality.
AI Engineer
Cleaning up retrieval pipelines to improve the accuracy of LLM responses.
Data Scientist
Evaluating the effectiveness of document retrieval strategies.
MLOps Engineer
Monitoring and debugging the signal-to-noise ratio in production RAG systems.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
JSONL Strict Parser
Robustly parse JSON Lines (.jsonl) strings into structured objects while isolating malformed lines.
agent-output-deduplicator
Detects and removes redundant outputs from multi-agent workflows using Jaccard similarity and n-gram overlap.
SSE Stream Reassembler
Reassembles fragmented Server-Sent Events (SSE) streams into a single coherent payload.
Orama Hybrid Search Query Builder
Generate syntactically perfect Orama search payloads with deterministic JSON structure.
X Ads (Twitter)
Connect your X Ads account to any AI agent. audit campaigns, analyze line item performance, and pull engagement reports through natural conversation.
Box
Store, share, and collaborate on files securely with enterprise-grade cloud content management and governance controls.
Bring your own AI
Change the model, client or framework. Keep Retrieval Relevance Scorer connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Retrieval Relevance Scorer.
The practical details behind the request, access and result.
How can I use Retrieval Relevance Scorer to stop my AI from hallucinating?
You use it to filter out irrelevant text before it ever reaches your agent. By scoring documents against the query, you ensure only the most relevant information is included in the prompt.
Does Retrieval Relevance Scorer work with any AI client?
Yes, as long as your client is MCP-compatible, such as Claude, Cursor, or Windsurf, you can use this to refine your context.
How does this MCP improve RAG accuracy?
It adds a layer of deterministic math—like TF-IDF and Jaccard similarity—to your retrieval process, ensuring the context is actually relevant to the user's specific words.
Can I see why certain documents were excluded from my search?
Yes, you can use the coverage analysis features to identify exactly which parts of a query were missing from your retrieved documents.
Is this better than just using vector similarity?
It's a different capability for a different job. Vector similarity finds things that are 'semantically similar,' while this MCP finds things that are 'mathematically relevant' to the specific terms used.
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.
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.
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.
One connection away
Give your agent a direct line to Retrieval Relevance Scorer.
Connect Retrieval Relevance Scorer once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available