Ragdrift MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 38 installs a week from npm. Last commit 13 Jun 2026.
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
Today is the operative word: we check Ragdrift MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ragdrift-mcp -- npx -y @mukundakatta/ragdrift-mcp
{
"mcpServers": {
"ragdrift-mcp": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/ragdrift-mcp"
]
}
}
}
[mcp_servers.ragdrift-mcp]
command = "npx"
args = ["-y", "@mukundakatta/ragdrift-mcp"]
{
"mcpServers": {
"ragdrift-mcp": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/ragdrift-mcp"
]
}
}
}
{
"servers": {
"ragdrift-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mukundakatta/ragdrift-mcp"
]
}
}
}
Market regime, 7-dimension risk vectors and payment hazard grades. Abstains when data is thin.
Release management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
Citation-guarded retrieval over 22M Taiwan court judgments and administrative interpretations
Production-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking.
Vehicle specs, federal recalls, complaints, TSBs, investigations and OBD-II DTC data for AI agents.
Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.
Answers built from our own checks of this server.