kpernyer/nyc-last-mile
If you are the rightful owner of nyc-last-mile 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.
The Model Context Protocol (MCP) server is designed to facilitate conversational AI queries through Claude Desktop, enabling users to interact with last-mile delivery analytics in a natural language format.
Tools
Functions exposed to the LLM to take actions
get_lane_clusters
Get all 5 behavioral clusters with summary statistics
get_lanes_in_cluster
List lanes in a specific cluster
get_lane_profile
Get metrics and cluster assignment for a lane
get_cluster_playbook
Recommended last-mile strategy for a cluster
find_similar_lanes
Find lanes with similar delivery patterns
get_early_delivery_analysis
Analyze early delivery patterns
get_regional_performance
Performance metrics for a ZIP3 region
get_friction_zones
Identify high-friction problem destinations
get_terminal_performance
Score terminals/DCs on outbound performance
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client