cco-mcp CLAUDE.md

cco-mcp CLAUDE.md is an instructions file for coding agents from toolprint/cco-mcp. It costs 1,286 tokens per session, scanned A, original, MIT.

A system for reviewing and approving Claude Code tool calls, with a Node.js and TypeScript server and a React dashboard. It supports rules for approvals and live dashboard updates through server-sent events, which push new information to a browser.

In plain words
What is it for?
Use it when developing or operating the CCO-MCP server and dashboard, including builds, development mode, formatting, linting, tests, inspection and approval configuration.
Why use it?
It gives teams a way to audit tool calls and apply approval rules instead of allowing every action without review. Its instructions also define how to build, run and test both parts of the project.

Instructions file

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 instructions/toolprint/cco-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/toolprint/cco-mcp

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 cco-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/toolprint/cco-mcp/claude-md.svg)](https://agentmods.dev/instructions/toolprint/cco-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/toolprint/cco-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/toolprint/cco-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,286 This file is loaded in full into every session.
When invoked 1,286 The same file — it is already loaded in full.
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 $0.01286 $0.01286
Opus 5 $0.00643 $0.00643
Sonnet 5 $0.00257 $0.00257
Haiku 4.5 $0.00129 $0.00129

Measured 5d ago against content hash c4f768d2227b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cco-mcp 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 5d 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 · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 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

CCO-MCP (Claude Code Oversight - Model Context Protocol) is a comprehensive audit and approval system for Claude Code tool calls. It consists of:

  • A Node.js/TypeScript MCP server backend with Express REST API
  • A React/TypeScript web dashboard UI
  • Real-time updates via Server-Sent Events (SSE)
  • Rule-based approval configuration system

Development Commands

Build Commands

# Build everything (backend + UI)
just build-all
# or
pnpm build:all

# Build backend only
just build
# or
pnpm build

# Build UI only
just build-ui
# or
pnpm build:ui

# Watch mode for backend
just build-watch
# or
pnpm build:watch

Development Commands

# Run both backend and UI in development mode
just dev-all
# or
pnpm dev:all

# Run backend only
just dev
# or
pnpm dev

# Run UI only
just dev-ui
# or
pnpm dev:ui

# Inspect MCP server
just inspect
# or
pnpm inspect

Code Quality Commands

# Format code
just format
# or
pnpm format

# Check formatting
just format-check
# or
pnpm format:check

# Lint
just lint
# or
pnpm lint

Testing Commands

# Run tests (currently echoes no tests configured)
just test
# or
pnpm test

# E2E tests with recording options
just e2e-test          # Without recording
just e2e-test-browser  # Browser recording only
just e2e-test-terminal # Terminal recording only
just e2e-test-full     # Both recordings

Architecture Overview

Backend Architecture

The backend follows a modular architecture:

  1. MCP Integration (src/server.ts)

    • Implements the MCP server with approval_prompt tool
    • Handles polling mechanism for approval/denial
    • Integrates with the audit service
  2. Express API (src/app.ts)

    • REST endpoints for audit logs and configuration
    • SSE endpoint for real-time updates
    • Static file serving for UI in production
  3. Audit Service (src/audit/)

Read the full file on GitHub · 235 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.

  1. 5d ago First seen · 235 lines · 1,286 tokens per session scan A c4f768d2227b

Subscribe to this mod's changes

cco-mcp CLAUDE.md is an instructions file published in the GitHub repository toolprint/cco-mcp (19 stars, last pushed 1y ago), licensed MIT. It adds 1,286 tokens to every session, about $0.0064 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.