Ragdrift Mcp
io.github.MukundaKattaPublished by GitHub account MukundaKattav0.1.1Updated Nov 3, 2026
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
Overview
Local MCP server that helps an assistant interpret RAG drift scores, pick thresholds and explain drift dimensions.
- What you can do
- Interpret a drift score for a given dimension, with severity classification and suggested next steps
- Recommend threshold values tuned to sample size and a false-positive budget
- Explain the five drift dimensions (data, embedding, response, confidence, query) as a structured reference
- When to use it
- Use it when you get RAG drift alerts and want an assistant to help judge whether a score is worrying and what to check next. It is an interpretation layer only; actual drift detection happens in the ragdrift libraries or your own telemetry.
- Requirements
- Runs locally over stdio, typically launched with npx from the npm package. No authentication, environment variables or headers are declared. Desktop MCP clients only; no web execution.
Installation
In SourceWeft
- Open Ragdrift Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
@mukundakatta/ragdrift-mcp
MCP server for diagnosing RAG drift. Lets an LLM reason about drift scores without needing to install Rust or PyO3.
Sibling to the ragdrift crate +
ragdrift-py PyPI wheel — this MCP
server is the interpretation layer; the actual drift detection happens in
those libraries (or your existing telemetry).
Tools
interpret_drift_score(score, dimension, threshold?)— plain-English interpretation, severity classification, suggested next steps.recommend_thresholds(dimension, sample_size, false_positive_budget)— threshold values tuned to your sample size and FP budget.explain_drift_dimensions()— structured reference for all 5 dimensions (data, embedding, response, confidence, query).
When to install
Install when you want Claude Desktop / Cursor / Cline / Windsurf / Zed to help diagnose RAG drift alerts. Example session:
User: "Got an embedding-drift alert with score 0.27 on a sample of 500. Should I be worried?"
LLM (calling
interpret_drift_score): "Score 0.27 on the embedding dimension lands in the 'significant shift, investigate' band. The underlying methods are MMD² (RBF kernel) and sliced Wasserstein-1. Likely next steps: did the embedding model change? Was the corpus re-indexed? Compare baseline and current document samples."
Install — Claude Desktop
Install — Cursor / Cline / Windsurf / Zed
Same shape per tool. npx -y @mukundakatta/ragdrift-mcp over stdio.
License
MIT OR Apache-2.0.
Source: packages/ragdrift-mcp/README.md at commit 6fad5bb
Tools
0Version history
1- v0.1.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts