Use BM25 Scorer with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Deterministic BM25 relevance scoring engine for RAG optimization.
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.
Complete set · 3 capabilities
The complete BM25 Scorer capability set.
These are the exact actions your AI can choose when you ask it to work with BM25 Scorer.
01-03
3 capabilities in this set.
Part of 3 available through BM25 Scorer.
- 01
Analyze document composition
Extracts statistics from a document
- 02
Calculate term weights
Computes the IDF for each term in a query
- 03
Compute relevance score
Calculates the BM25 relevance score for a document
Observed, not estimated
643ms average. Fast in production.
BM25 Scorer is checked daily against the live service.
- Fastest day
- 540ms
- Slowest day
- 824ms
- 14-day trend
- Improving-8%
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 BM25 Scorer, so you can see the experience inside your AI.
It does not authenticate your account with BM25 Scorer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
BM25 Scorer Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_13iaLV42ZXoIPJuXWoZJmsXXcpfHRxpcEFkqQcfP/mcpClaude 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 — BM25 Scorer capabilities are ready to use.
{
"mcpServers": {
"bm25-context-relevance-scorer-mcp": {
"url": "https://edge.vinkius.com/vk_preview_13iaLV42ZXoIPJuXWoZJmsXXcpfHRxpcEFkqQcfP/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
FAQ
Questions BM25 Scorer owners ask.
- 01
How does the scoring work?
The engine uses the BM25 algorithm, calculating IDF based on corpus size and term prevalence, then applying length normalization and saturation constants.
- 02
Do I need an LLM to calculate scores?
No, this capability provides deterministic mathematical results using the compute_relevance_score function without any LLM involvement.
- 03
What inputs are required for scoring?
You must provide query tokens, document tokens, corpus size, term document counts, and average document length.
Explore
More in Data Science
Retrieval Relevance Scorer AI Connector
A deterministic scoring engine that filters retrieved documents using Jaccard, TF-IDF, and coverage metrics.
ViewLead Scoring Calculator AI Connector
Calculate a lead's conversion readiness score instantly using configurable firmographic and behavioral data po
ViewMarketMuse (AI Content Strategy & SEO) AI Connector
Plan and optimize content via MarketMuse AI — analyze topic authority, generate content briefs, and audit SEO
ViewLife Satisfaction Wheel AI Connector
Quantify and analyze balance across essential life dimensions.
View
Suggestions
NPS Score Calculator AI Connector
Calculate Net Promoter Score, performance tiers, and statistical margin of error.
ViewAgent Cost Allocation Engine AI Connector
Deterministic cost allocation and chargeback calculator for multi-agent systems.
ViewPrompt Template Reuse Analyzer AI Connector
A diagnostic engine to evaluate prompt library efficiency and identify consolidation opportunities.
ViewPrompt Reuse Analyzer AI Connector
Analyze prompt template reuse, efficiency, and standardization opportunities.
View
