Ragdrift Mcp
Exposes three tools that help LLMs interpret alerts from a RAG drift monitoring system. When your retrieval pipeline drifts across dimensions like coverage, rank correlation, or embedding shift, interpret_drift_score translates raw metrics into plain English explanations. recommend_thresholds suggests sensible alerting boundaries based on your pipeline's characteristics, and explain_drift_dimensions breaks down what each of the five drift axes actually measures. Part of a fourteen server collection from the mcp-stack monorepo, this one wraps logic from the ragdrift Rust crate. Install it if you're building agents that triage production RAG quality issues or need to turn numerical drift scores into actionable diagnosis without hallucinating what the metrics mean.
- tools
- 3
- transport
- STDIO
- last updated
- May 10, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
interpret_drift_scoreLLM diagnoses RAG drift alerts
LLM diagnoses RAG drift alerts
No parameter schema in public metadata yet.
recommend_thresholds
No parameter schema in public metadata yet.
explain_drift_dimensions
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
mcp-stack
Fourteen small MCP servers for everyday LLM / RAG / agent work. Each ships independently on npm, listed in the official MCP Registry, and is callable from Claude Desktop, Cursor, Cline, Windsurf, Zed, and any other MCP-compatible client.
RAG / agent helpers
| Package | Tools | When to install |
|---|---|---|
@mukundakatta/promptbudget-mcp | truncate_to_token_budget | LLM needs to fit text into a context window mid-task |
@mukundakatta/citecite-mcp | inject_citations, parse_citations, strip_citations | Round-trip [1] [2] markers in RAG outputs |
@mukundakatta/ragmetric-mcp | recall_at_k, hit_at_k, mrr, ndcg_at_k, evaluate_batch | LLM helps score retrieval quality |
@mukundakatta/ragdrift-mcp | interpret_drift_score, recommend_thresholds, explain_drift_dimensions | LLM diagnoses RAG drift alerts |
Reliable transforms LLMs reach for tools instead of imagining
Details
- Repository
- github.com/mukundakatta/mcp-stack
- Category
- AI & LLM Tools
- Package
@mukundakatta/ragdrift-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from mukundakatta
Related AI & LLM Tools MCP servers
View all
AgentDilemmapatrickbakowski/agent-dilemma-skillSubmit a dilemma for blind community verdict with reasoning to improve low confidence0stars
Ryvo Protocolryvonetwork/ryvo-agenticMCP server for Ryvo Protocol state reads and prepare-only payment-channel actions.0stars
Publish Gate (lite)skibuff22/agent-ops-kit-liteCheck a draft's numbers against your facts.md and its links before you publish.0stars
Memdatathelabvenice/memdata-mcpPersistent memory for AI agents. Store context, retrieve it semantically.0stars
Reviewmetricvktr93/reviewmetric-mcpAn MCP server connecting Claude to the Review Metric 15-agent scientific peer review pipeline.0stars
Whaber Oraclewhawi/oracle-agent-cardGround truth operational layer for urban transfers in LatAm.0stars