dbus-mcp: Instructions file for Claude Code

CLAUDE.md

dbus-mcp CLAUDE.md is an instructions file for Claude Code from aaronsb/dbus-mcp. It costs 1,924 tokens per session, scanned B, original, MIT.

Repository instructions for a Linux server that connects AI assistants to D-Bus, Linux's system for letting applications and desktop services communicate.

In plain words
What is it for?
Use them when adding D-Bus tools, Linux desktop or system integrations, distribution profiles, permissions, or monitoring features.
Why use it?
They describe the server's structure and security boundaries, helping changes fit the right layer and avoid exposing unsafe system operations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is aaronsb/dbus-mcp's own configuration. It tells Claude Code how to work on dbus-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dbus-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/aaron/Projects/ai/mcp/dbus-mcp.

Reuse

Borrowing it

Nothing to install: this file belongs to aaronsb/dbus-mcp. 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/aaronsb/dbus-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/aaronsb/dbus-mcp

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.

agentmods badge for dbus-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aaronsb/dbus-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/aaronsb/dbus-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aaronsb/dbus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronsb/dbus-mcp/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.

agentmods 80×15 button for dbus-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aaronsb/dbus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronsb/dbus-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,924 This file is loaded in full into every session.
When invoked 1,924 The same file — it is already loaded in full.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01924 $0.01924
Opus 5.5 $0.00770 $0.00770
Sonnet 5.5 $0.00385 $0.00385
Haiku 4.5 $0.00192 $0.00192

Measured 2mo ago against content hash de583c6d5104, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

dbus-mcp CLAUDE.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo nano /etc/dbus-mcp/config # Set SAFETY_LEVEL="medium"
CLAUDE.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 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

D-Bus MCP Server - A Model Context Protocol server that bridges AI assistants with D-Bus system and session buses on Linux systems.

While Linux powers everything from vacuum cleaners to supercomputers, this server focuses on two major system roles:

  1. Workstation Role: Interactive desktop/laptop systems where AI assists users with productivity tasks
  2. Dedicated System Role: Purpose-built systems (servers, routers, NAS, embedded devices) where AI performs remote monitoring and management

Architecture

The project follows a modular architecture:

  • MCP Server Core: Handles protocol, tool registration, request/response
  • System Profiles: Adapts to specific distros/desktops (KDE/Arch, GNOME/Ubuntu, etc.)
  • D-Bus Manager: Manages session/system bus connections
  • Security Layer: Enforces policies, whitelists safe operations
  • Tool Implementations: Individual tools for specific D-Bus operations

Key Design Documents

  • README.md: Project overview and vision
  • docs/README.md: Documentation index

Design Documents (docs/design/)

  • CONCEPT.md: High-level overview and use cases
  • USE-CASES-RANKED.md: Prioritized capabilities by system role
  • SERVER-FLEET-CONCEPT.md: "Maintenance robot" model for dedicated systems
  • SYSTEM-ROLES.md: Linux system diversity and role definitions

Architecture Documents (docs/architecture/)

  • ARCHITECTURE-OVERVIEW.md: Visual architecture and dual use cases
  • ARCHITECTURE-DECISIONS.md: SystemD integration and deployment architecture
  • CONNECTION-ARCHITECTURE.md: Client-server-systemd connection model
  • SYSTEM-PROFILES.md: Modular adaptation to different distros/desktop environments
  • LANGUAGE-EVALUATION.md: Language comparison and Python selection rationale
  • PROJECT-STRUCTURE.md: Detailed project organization and module descriptions

Implementation Guides (docs/guides/)

  • TOOL-PRESENTATION.md: Strategy for presenting tools to AI clients
  • TOOL-HIERARCHY.md: Progressive disclosure and tool organization
  • SECURITY.md: Comprehensive security architecture
  • PRIVILEGE-MODEL.md: Privilege separation and context handling
  • CONTEXT-EXAMPLES.md: Real-world context scenarios and security patterns
  • DISCOVERED-CAPABILITIES.md: Live system exploration findings
  • EXAMPLES.md: Usage examples and best practices

Read the full file on GitHub · 213 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. 2mo ago First seen · 213 lines · 1,924 tokens per session scan B de583c6d5104

Subscribe to this mod's changes

dbus-mcp CLAUDE.md is an instructions file published in the GitHub repository aaronsb/dbus-mcp (4 stars, last pushed 1y ago), licensed MIT. It adds 1,924 tokens to every session, about $0.0077 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

dbus-mcp CLAUDE.md compared with instructions from other repositories

dbus-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dbus-mcp CLAUDE.mdaaronsb/dbus-mcpInstructions file41y agoMITB1,924Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode