adhit-r/fairmind-mcp
If you are the rightful owner of fairmind-mcp 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.
FairMind MCP is a Model Context Protocol server designed to enable AI agents to verify and self-correct bias in real-time using Green AI principles.
Tools
Functions exposed to the LLM to take actions
evaluate_bias
Evaluates text, code, or data for bias against protected attributes.
evaluate_bias_advanced
Advanced evaluation with full Fairlearn MetricFrame and AIF360 support.
compare_code_bias
Compares two code snippets for structural bias.
generate_counterfactuals
Generates alternative text suggestions to reduce bias.
evaluate_model_outputs
Batch evaluation tool for testing multiple LLM/fine-tuned model outputs.
evaluate_prompt_suite
Systematic prompt suite testing with tracking over time.
evaluate_model_response
Real-time single output testing for quick bias checks during inference.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client