What is mcpli CLAUDE.md?

A repository instruction file for MCPLI, a TypeScript command-line tool that turns Model Context Protocol servers into command-line tools. It documents command syntax, daemon identity, environment variables, and file layout.

Use it when modifying MCPLI, especially its command structure, macOS launchd process management, environment handling, or repository organization.

It gives coding agents the project rules needed to make changes without misunderstanding how commands, persistent processes, or environments are separated.

How cameroncooke/mcpli configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cameroncooke/mcpli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cameroncooke/mcpli/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cameroncooke/mcpli

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cameroncooke/mcpli/claude-md/github.svg)](https://agentmods.dev/instructions/cameroncooke/mcpli/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cameroncooke/mcpli/claude-md"><img src="https://agentmods.dev/badge/instructions/cameroncooke/mcpli/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cameroncooke/mcpli/claude-md"><img src="https://agentmods.dev/badge/instructions/cameroncooke/mcpli/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,366 This file is loaded in full into every session.

When invoked 1,366 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01366	$0.01366
Opus 5.5	$0.00546	$0.00546
Sonnet 5.5	$0.00273	$0.00273
Haiku 4.5	$0.00137	$0.00137

Measured 2mo ago against content hash dd4ef9e1b269, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpli CLAUDE.md 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 2mo 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.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

MCPLI is a TypeScript CLI tool that transforms stdio-based MCP (Model Context Protocol) servers into first-class command-line tools. It maintains persistent daemon processes for fast, stateful tool execution using macOS launchd for process orchestration.

Key Architecture Principles

Command Structure

Always requires explicit server command: mcpli <tool> [options] -- <mcp-server-command> [args...]
No default daemon selection: Every invocation must specify the MCP server command after --
Environment-aware daemon isolation: Different server commands, arguments, or environment variables create separate daemons

Daemon Identity and Environment Variables

CRITICAL: Environment variables work differently for daemon identity vs MCP server execution:

Daemon Identity: Only considers environment variables specified AFTER the -- as part of the server command
- mcpli tool -- ENV_VAR=value node server.js → daemon ID includes ENV_VAR
- ENV_VAR=value mcpli tool -- node server.js → daemon ID does NOT include ENV_VAR (same daemon as without ENV_VAR)
MCP Server Environment: Environment variables before -- affect mcpli itself, not the daemon identity
- Shell environment where mcpli runs should not influence daemon uniqueness
- Only explicit environment in the server command affects daemon hashing

File Structure

Entry point: src/mcpli.ts - CLI argument parsing and tool execution
Daemon system: src/daemon/ - Persistent process management using launchd
- client.ts - Daemon client for IPC communication
- runtime.ts - Core orchestrator interface and daemon identity logic
- runtime-launchd.ts - macOS launchd-based orchestrator implementation
- wrapper.ts - In-process daemon wrapper
- commands.ts - Daemon command handling and execution
- ipc.ts - Unix socket IPC communication
Test servers: weather-server.js, test-server.js, complex-test-server.js

Read the full file on GitHub · 125 lines

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.

2mo ago First seen · 125 lines · 1,366 tokens per session scan A dd4ef9e1b269

Subscribe to this mod's changes

mcpli CLAUDE.md is an instructions file published in the GitHub repository cameroncooke/mcpli (104 stars, last pushed 8mo ago), licensed MIT. It adds 1,366 tokens to every session, about $0.0055 per session on Opus 5.5. 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.

mcpli CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcpli CLAUDE.mdcameroncooke/mcpli	Instructions file	104	8mo ago	MIT	A	1,366	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcpli: Instructions file for Claude Code