mcp

Piebald-AI's avatarfrom Piebald-AI

Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.

⭐78stars🔀6forks📁View on GitHub🕐Updated Jan 3, 2026
[Agent Observability]

When & Why to Use This Skill

This Claude skill provides a comprehensive interface for Splitrail's MCP (Model Context Protocol) server, enabling AI assistants to programmatically query and analyze usage statistics, costs, and model performance. It serves as a vital tool for developers and teams to monitor AI tool efficiency, track resource consumption, and manage infrastructure through a standardized protocol.

Use Cases

  • AI Usage Monitoring: Programmatically retrieve daily usage statistics and model distribution to understand how AI resources are being utilized across different projects.
  • Cost Management and Optimization: Access detailed cost breakdowns over specific date ranges to identify high-cost operations and optimize budget allocation for AI services.
  • Tool Performance Comparison: Compare usage patterns and efficiency across various AI coding tools to determine the most effective solutions for specific development tasks.
  • Infrastructure Customization: Follow the integrated guide to add custom tools and resources to the MCP server, tailoring the AI's data access to specific organizational needs.
namemcp
descriptionGuide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.

MCP Server

Splitrail can run as an MCP server, allowing AI assistants to query usage statistics programmatically.

cargo run -- mcp

Source Files

  • src/mcp/mod.rs - Module exports
  • src/mcp/server.rs - Server implementation and tool handlers
  • src/mcp/types.rs - Request/response types

Available Tools

  • get_daily_stats - Query usage statistics with date filtering
  • get_model_usage - Analyze model usage distribution
  • get_cost_breakdown - Get cost breakdown over a date range
  • get_file_operations - Get file operation statistics
  • compare_tools - Compare usage across different AI coding tools
  • list_analyzers - List available analyzers

Resources

  • splitrail://summary - Daily summaries across all dates
  • splitrail://models - Model usage breakdown

Adding a New Tool

  1. Define the tool handler in src/mcp/server.rs using the #[tool] macro
  2. Add request/response types to src/mcp/types.rs if needed

See existing tools in src/mcp/server.rs for the pattern.

Adding a New Resource

  1. Add URI constant to resource_uris module in src/mcp/server.rs
  2. Add to list_resources() method
  3. Handle in read_resource() method