bridge-mcp CLAUDE.md

bridge-mcp CLAUDE.md is an instructions file for coding agents from muchiny/bridge-mcp. It costs 4,830 tokens per session, scanned A, original, MIT.

Project instructions and command references for Bridge MCP, a service that lets Claude Code run commands on remote or isolated computers through SSH.

In plain words
What is it for?
Use them to inspect or operate Docker, Kubernetes, Linux, and Windows environments through Bridge MCP tools or its command-line interface.
Why use it?
They help an agent understand the project and choose the right command interface for remote system work.

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/muchiny/bridge-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/muchiny/bridge-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 bridge-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/muchiny/bridge-mcp/claude-md.svg)](https://agentmods.dev/instructions/muchiny/bridge-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/muchiny/bridge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/muchiny/bridge-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,830 This file is loaded in full into every session.
When invoked 4,830 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 $0.04830 $0.04830
Opus 5 $0.02415 $0.02415
Sonnet 5 $0.00966 $0.00966
Haiku 4.5 $0.00483 $0.00483

Measured 4d ago against content hash 1c92685f4c35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bridge-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 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.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

Bridge MCP (binary bridge-mcp, formerly MCP SSH Bridge / mcp-ssh-bridge) is a Rust MCP server that enables Claude Code to securely execute commands on air-gapped environments via SSH. JSON-RPC over stdio, strict security controls. 476 tools across 77 groups (62 Linux, 13 Windows, 2 cross-platform). Count source of truth: .migration-baseline.json (python3 scripts/validate_baseline.py).

CLI-as-Tool Mode (Alternative to MCP)

All 476 MCP tools are accessible directly via CLI, enabling 10-32x token savings compared to MCP mode. Use CLI for dev workflows, MCP for enterprise integration.

Quick Reference

# Invoke any tool directly (same as MCP, but via CLI)
bridge-mcp tool ssh_docker_ps host=prod
bridge-mcp tool ssh_exec host=prod command="df -h" --json
bridge-mcp tool ssh_k8s_get --json-args '{"host":"k8s","resource":"pods","namespace":"default"}'

# Progressive discovery (token-efficient for AI agents)
bridge-mcp list-tools --groups-only          # 77 groups (~2K tokens)
bridge-mcp list-tools --group docker          # tools in group (~500 tokens)
bridge-mcp list-tools --search kubernetes     # keyword search
bridge-mcp describe-tool ssh_docker_ps        # full schema + Reduction Strategy (~200 tokens)
bridge-mcp describe-tool ssh_exec --json      # schema as JSON

# Global --json flag works on all commands
bridge-mcp --json status
bridge-mcp --json tool ssh_service_status host=web1 service=nginx

Token-efficient patterns (IMPORTANT for AI agents)

Always call describe-tool before invoking an unknown tool — its top-of-output Reduction Strategy line tells you which params apply. Server-side filtering runs BEFORE truncation, so you never lose data to the output cap.

Output kind Strategy Example
Tabular (docker_ps, service_list) columns + limit columns='["NAME","STATUS"]' limit=20
Json (k8s_get, docker_inspect, awx_*) jq_filter + output_format=tsv jq_filter='.items[] | [.name, .status]' output_format=tsv (60-80% savings)
Yaml yq_filter + output_format=tsv same shape as jq
Auto Any of the above tool auto-detects
RawText (logs, ssh_exec) save_output=/tmp/out.txt read file locally afterwards

Read the full file on GitHub · 315 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. 4d ago First seen · 315 lines · 4,830 tokens per session scan A 1c92685f4c35

Subscribe to this mod's changes

bridge-mcp CLAUDE.md is an instructions file published in the GitHub repository muchiny/bridge-mcp (8 stars, last pushed 4d ago), licensed MIT. It adds 4,830 tokens to every session, about $0.0242 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 2026-08-31.