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.
npx agentmods add instructions/apify/mcpc/claude-mdgit clone --depth 1 https://github.com/apify/mcpcWhat 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 | $0.12611 | $0.12611 |
| Opus 5 | $0.06305 | $0.06305 |
| Sonnet 5 | $0.02522 | $0.02522 |
| Haiku 4.5 | $0.01261 | $0.01261 |
Grade A, and why
mcpc 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 853 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.
Project Overview
mcpc is a universal command-line client for the Model Context Protocol (MCP),
which maps MCP to intuitive CLI commands for shell access, scripts, and AI coding agents.
mcpc can connect to any MCP server over Streamable HTTP or stdio transports,
securely login via OAuth credentials and store credentials,
and keep long-term sessions to multiple servers in parallel.
It supports all major MCP features, including tools, resources, prompts, asynchronous tasks, and notifications.
mcpc is handy for manual testing of MCP servers, scripting,
and AI coding agents to use MCP in "code mode",
for better accuracy and lower tokens compared to traditional tool function calling.
After all, UNIX-compatible shell script is THE most universal coding language, for both people and LLMs.
Key capabilities:
- Universal MCP client - Works with any MCP server over Streamable HTTP or stdio
- Persistent sessions - Keep multiple server connections alive simultaneously
- Zero setup - Connect to remote servers instantly with just a URL
- Full protocol support - Tools, resources, prompts, dynamic discovery, and async notifications
--jsonoutput - Easy integration withjq, scripts, and other CLI tools- AI-friendly - Designed for code generation and automated workflows
- Secure - OS keychain integration for credentials, encrypted auth storage
Build and Development Commands
# Install dependencies
pnpm install
# Build the project
pnpm run build
# Run tests
pnpm test
# Test locally after building
pnpm link --global
mcpc --help
# Run linter/formatter (if configured)
pnpm run lint
pnpm run format
Quick Start Examples
# List all active sessions and saved authentication profiles
mcpc
# Login to OAuth-enabled MCP server and save authentication for future use
mcpc login mcp.apify.com
# Create a persistent session
mcpc connect mcp.apify.com @test
mcpc @test # show session info
mcpc @test tools-list # list available tools
mcpc @test tools-call search-actors query:="web crawler"
# Use JSON mode for scripting
mcpc --json @test tools-list
# Use a local server package referenced by MCP config file
mcpc connect ~/.vscode/mcp.json:filesystem @fs
mcpc @fs tools-list
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.
- 2d ago First seen · 853 lines · 12,611 tokens per session scan A 019dd8f08dbb
mcpc CLAUDE.md is an instructions file published in the GitHub repository apify/mcpc (761 stars, last pushed yesterday), licensed Apache-2.0. It adds 12,611 tokens to every session, about $0.0631 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.
Other instructions, from other repositories
voice_typing AGENTS.md
AGENTS.md instructions for themanyone/voice_typing, covering agents guide: voice typing project, core components, modes of operation, architecture & patterns and producer-consumer pattern.
vue-tui AGENTS.md
Instructions for vuejs-ai/vue-tui, covering common pitfalls & best practices, project context records (pcr), using vite+, the unified toolchain for the web and review checklist.
axe AGENTS.md
Instructions for jrswab/axe, covering axe — agents.md, what this is, design philosophy, non-obvious constraints and what good contributions look like.
mirage CLAUDE.md
Claude Code instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
UniCli CLAUDE.md
Instructions for yucchiy/UniCli, covering unicli, project structure, quick commands, build protocol (must be built first to trigger file copy) and build client.
autospec AGENTS.md
Instructions for ariel-frischer/autospec, covering agents.md, prerequisites, commands, build & dev and single test.