Ragdrift MCP Server
by mukundakattaio.github.MukundaKatta/ragdrift-mcpv0.1.1
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
context tax
queued
security
queued
cold start
queued
freshness
Slowing4mo ago
Install Ragdrift MCP server
Install in Claude Code
claude mcp add ragdrift -- npx -y @mukundakatta/ragdrift-mcpInstall in Cursor
{
"mcpServers": {
"ragdrift": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/ragdrift-mcp"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"ragdrift": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/ragdrift-mcp"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"ragdrift": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mukundakatta/ragdrift-mcp"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"ragdrift": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/ragdrift-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Slowing — last maintenance signal 4mo ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-06-13 · 4mo ago · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-05-10 · 5mo ago · official registry · v0.1.1
FAQ
›How do I install the Ragdrift MCP server in Claude Code?
Run: claude mcp add ragdrift -- npx -y @mukundakatta/ragdrift-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Ragdrift require an API key?
No required environment variables are declared in its published metadata.
›Can I use Ragdrift as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Ragdrift in the official MCP registry?
Yes, as io.github.MukundaKatta/ragdrift-mcp.
Alternatives to Ragdrift
Other memory MCP servers.
MemoryActiveKnowledge graph-based persistent memory for maintaining context.
HindsightActiveHindsight: long-term memory for AI agents modeled on human memory.
Codebase MemoryActiveIndexes a repo into a persistent local knowledge graph of functions, classes, call chains, HTTP routes and cross-service links, using tree-sitter and LSP.
CogneeActiveMemory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
HonchoActiveMemory that reasons: continual learning for stateful agents. Better context, fewer tokens.
Basic MemoryActiveLocal-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, with optional cloud sync and team workspaces.