mcp-help

mcp-help is a command for Claude Code from elvatis/elvatis-mcp. It costs 0 tokens per session (1,270 once invoked), scanned A, original, Apache-2.0.

A formatted help command for the elvatis-mcp server, which provides tools for routing tasks to different AI assistants and services. It can show the full guide, one tool's details, or a recommendation for a described task.

In plain words
What is it for?
Use it to look up a tool's category, parameters, and example, view the complete guide, or ask which tool fits a task.
Why use it?
It makes a large tool guide easier to read and helps choose a suitable backend without exposing raw tool output.

Command for Claude Code

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/elvatis/elvatis-mcp/mcp-help
Clone the repo
git clone --depth 1 https://github.com/elvatis/elvatis-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 mcp-help

README.md
[![agentmods](https://agentmods.dev/badge/commands/elvatis/elvatis-mcp/mcp-help.svg)](https://agentmods.dev/commands/elvatis/elvatis-mcp/mcp-help)
Your own site
<a href="https://agentmods.dev/commands/elvatis/elvatis-mcp/mcp-help"><img src="https://agentmods.dev/badge/commands/elvatis/elvatis-mcp/mcp-help.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,270 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 $0.00000 $0.01270
Opus 5 $0.00000 $0.00635
Sonnet 5 $0.00000 $0.00254
Haiku 4.5 $0.00000 $0.00127

Measured 4d ago against content hash fb153b1942ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-help 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/commands/mcp-help.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are showing the elvatis-mcp tool guide. Present ALL output as your own formatted text (never just show raw MCP tool results).

If $ARGUMENTS is empty, show the FULL guide below as your own output, formatted exactly as written.

If $ARGUMENTS contains a tool name (e.g. "openclaw_status", "home_light", "prompt_split"), show ONLY that tool's help using the reference below. Format it as:

tool_name

Category: (from the section it belongs to) Description: (from the reference) Parameters: (list the parameters with types and descriptions) Example: (show a realistic usage example)

If $ARGUMENTS contains a task description (not a tool name), call mcp_help with that task, then present the recommendation formatted as your own text.


elvatis-mcp: Sub-Agent Routing Guide (34 tools)

Sub-Agents

Tool Backend Strengths
claude_run Claude (Anthropic) Complex reasoning, writing, code review. Use when client is not Claude.
openclaw_run OpenClaw (plugins) Trading, automations, custom workflows
gemini_run Google Gemini Long context (1M), multimodal, fast analysis
codex_run OpenAI Codex Coding, debugging, refactoring, file editing
local_llm_run Local LLM Free, private, classify/format/extract/rewrite

Home Automation

Tool Description
home_get_state Get current state of any HA entity (light, climate, sensor, switch, vacuum, media_player)
home_light Control a light: on/off/toggle, brightness (0-100%), color temperature, RGB color
home_climate Control Tado thermostats: target temperature or HVAC mode (heat/auto/off)
home_scene Activate a Hue scene in a room (wohnzimmer, flur, kuche, schlafzimmer, home)
home_vacuum Control the Roborock: start clean, stop, return to dock, or get status
home_sensors Read all environmental sensors: temp, humidity, CO2 for all rooms + outside
home_automation List, trigger, enable, or disable HA automations

Read the full file on GitHub · 105 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 · 105 lines · 0 tokens per session scan A fb153b1942ed

Subscribe to this mod's changes

mcp-help is a command published in the GitHub repository elvatis/elvatis-mcp (0 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,270 tokens. 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.