mcp

mcp is a skill for Claude Code, Codex from Piebald-AI/splitrail. It costs 26 tokens per session (333 once invoked), scanned A, original, MIT.

A development guide for Splitrail’s MCP server, an interface that lets AI assistants query Splitrail’s usage statistics. It explains how to add tools and resources, which are callable operations and readable data endpoints.

In plain words
What is it for?
Use it to add or modify queries for daily statistics, model usage, costs, file operations, tool comparisons, analyzers, or summary resources.
Why use it?
It shows where request types, handlers, and resource URLs belong when extending the server interface.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/piebald-ai/splitrail/mcp
Any agent
npx skills add Piebald-AI/splitrail --skill mcp
Clone the repo
git clone --depth 1 https://github.com/Piebald-AI/splitrail

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/piebald-ai/splitrail/mcp.svg)](https://agentmods.dev/skills/piebald-ai/splitrail/mcp)
Your own site
<a href="https://agentmods.dev/skills/piebald-ai/splitrail/mcp"><img src="https://agentmods.dev/badge/skills/piebald-ai/splitrail/mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00333
Opus 5 $0.00013 $0.00167
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00003 $0.00033

Measured 4d ago against content hash eb12c6848dce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/mcp/SKILL.md · 46 lines

What it actually says

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
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 46 lines · 26 tokens per session scan A eb12c6848dce

Subscribe to this mod's changes

mcp is a skill published in the GitHub repository Piebald-AI/splitrail (218 stars, last pushed 13d ago), licensed MIT. It adds 26 tokens to every session and 333 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.