configure

configure is a command for coding agents from RandomSynergy17/Arcane-MCP-Server. It costs 10 tokens per session (1,228 once invoked), scanned A, original, MIT.

A configuration command for choosing which Arcane tools Claude Code can see. Arcane connects Claude Code to Docker management through an MCP server.

In plain words
What is it for?
Use it to choose a ready-made tool set, such as read-only Docker inspection or deployment work, or to create a custom selection. It saves the choices in Arcane’s configuration file.
Why use it?
Showing every available tool can fill Claude Code’s context with options you do not need. This command lets you limit the visible tools by preset, module, or individual tool.

Command

Part of the arcane-mcp-server plugin — 1 skill, 1 command, 1 MCP server shipped together

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 commands/randomsynergy17/arcane-mcp-server/configure
Clone the repo
git clone --depth 1 https://github.com/RandomSynergy17/Arcane-MCP-Server

Or install arcane-mcp-server, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 MCP server.

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 configure

README.md
[![agentmods](https://agentmods.dev/badge/commands/randomsynergy17/arcane-mcp-server/configure.svg)](https://agentmods.dev/commands/randomsynergy17/arcane-mcp-server/configure)
Your own site
<a href="https://agentmods.dev/commands/randomsynergy17/arcane-mcp-server/configure"><img src="https://agentmods.dev/badge/commands/randomsynergy17/arcane-mcp-server/configure.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,228 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00010 $0.01228
Opus 5 $0.00005 $0.00614
Sonnet 5 $0.00002 $0.00246
Haiku 4.5 $0.00001 $0.00123

Measured 5d ago against content hash 35d4f85cedbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

configure 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.

commands/configure.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/arcane:configure — Tool filter setup

Use this slash command to trim which Arcane MCP tools are exposed to Claude Code. The full server registers 180 tools; surfacing all of them in tools/list bloats the context window. This command writes a tools block to ~/.arcane/config.json that selects a preset, module allowlist, and per-tool overrides. The Arcane MCP server picks up changes live when its config watcher is attached.

Workflow

  1. Ask the user to pick a preset with AskUserQuestion, single-select:

    • commonly-used — containers, images, projects (stacks), volumes, networks (~52 tools) (recommended default)
    • read-only — every *_list / *_get / *_inspect / *_stats / *_status / *_summary tool (~60 tools)
    • minimal — dashboard + container list/get/counts (5 tools)
    • deploy — project, gitops, template, registry, environment, build (~40 tools)
    • full — all 180 tools (current default if the user has never configured this)
    • custom — fine-tune modules and individual tools
  2. If the user picks custom (or says they want to fine-tune after picking another preset):

    • Ask which modules to enable via AskUserQuestion multi-select. The 25 module names: auth, build, container, dashboard, environment, event, gitops, image, image-update, job, network, network-topology, notification, port, project, registry, settings, swarm, system, template, updater, user, volume, vulnerability, webhook.
    • Optionally ask if they want per-tool adjustments. If yes, iterate module-by-module (never more than ~10 options per AskUserQuestion step) showing each module's tools so they can add/remove individual entries.
  3. Build the tools block — only include the fields that are non-empty:

    {
      "tools": {
        "preset": "<chosen>",
        "modules": ["<optional allowlist>"],
        "enabled": ["<optional additions>"],
        "disabled": ["<optional subtractions>"]
      }
    }
    

Read the full file on GitHub · 66 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 · 66 lines · 10 tokens per session scan A 35d4f85cedbd

Subscribe to this mod's changes

configure is a command published in the GitHub repository RandomSynergy17/Arcane-MCP-Server (13 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 1,228 once invoked, about $0.0001 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.