saranshhalwai/drift-detector
3.1
If you are the rightful owner of drift-detector and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
Drift Detector is an MCP server designed to monitor and detect drift in LLM performance over time using MCP's sampling functionality.
Tools
Functions exposed to the LLM to take actions
run_initial_diagnostics
Establishes a baseline for model behavior using adaptive sampling techniques.
check_drift
Measures potential drift by comparative sampling against the baseline.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client