What is agent-ruler-openmcp?

A guide to installing and operating OpenMCP, an npm package and command-line tool for managing a local gateway and connected services.

Installing or upgrading OpenMCP, starting and diagnosing its gateway, configuring skills, checking logs, and testing or publishing the command-line tool.

It removes guesswork around installation, upgrades, startup, logs, configuration, and troubleshooting, including the required Node.js version and default gateway address.

agent-ruler-openmcp — Skill for Codex by LSTM-Kirigaya/openmcp-client

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.

Any agent

npx skills add LSTM-Kirigaya/openmcp-client --skill agent-ruler-openmcp

Clone the repo

git clone --depth 1 https://github.com/LSTM-Kirigaya/openmcp-client

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lstm-kirigaya/openmcp-client/agent-ruler-openmcp/github.svg)](https://agentmods.dev/skills/lstm-kirigaya/openmcp-client/agent-ruler-openmcp)

Your own site

<a href="https://agentmods.dev/skills/lstm-kirigaya/openmcp-client/agent-ruler-openmcp"><img src="https://agentmods.dev/badge/skills/lstm-kirigaya/openmcp-client/agent-ruler-openmcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lstm-kirigaya/openmcp-client/agent-ruler-openmcp"><img src="https://agentmods.dev/badge/skills/lstm-kirigaya/openmcp-client/agent-ruler-openmcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,208 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 177
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 178
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.01208
Opus 5.5	$0.00032	$0.00483
Sonnet 5.5	$0.00016	$0.00242
Haiku 4.5	$0.00008	$0.00121

Measured 2mo ago against content hash e23aefbce575, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-ruler-openmcp 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 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.

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.

cli/skills/agent-ruler-openmcp/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Ruler OpenMCP

Use this skill to help users install and operate the @agent-ruler/openmcp npm package. Prefer npm commands and the openmcp binary in all user-facing examples.

Package Facts

npm package: @agent-ruler/openmcp
CLI binary: openmcp
Minimum Node.js: >=18
Default Gateway WebSocket: ws://localhost:8282
Default Gateway logs directory: %USERPROFILE%\.openmcp\logs\gateway on Windows, ~/.openmcp/logs/gateway on Unix-like systems

Install Or Upgrade

For normal users, recommend a global npm install:

npm install -g @agent-ruler/openmcp
openmcp --version
openmcp --help

To upgrade an existing global install:

npm install -g @agent-ruler/openmcp@latest
openmcp --version

If a specific release is needed:

npm install -g @agent-ruler/[email protected]

Avoid telling users to run yarn openmcp ...; global npm users should run openmcp ... directly.

First Run Workflow

Start Gateway before running commands that call service controllers:

openmcp gateway start
openmcp gateway status

If startup fails or status is not running, ask for these diagnostics:

openmcp gateway logs -n 200
openmcp gateway logs-dir
openmcp gateway run -p 8282

Use gateway run when the user needs foreground stderr/stdout. Use gateway logs for background failures; it should include both gateway.log and gateway-startup.log.

If the Gateway uses a non-default port, pass -g to commands that talk to it:

openmcp mcp server list -g ws://127.0.0.1:9000

Common Commands

Show help and versions:

openmcp --help
openmcp gateway --help
openmcp mcp --help
openmcp debug --help

Manage Gateway:

openmcp gateway start
openmcp gateway status
openmcp gateway logs -n 200
openmcp gateway stop

Add and connect an MCP server from a file:

openmcp mcp server add --file ./mcp-server.json
openmcp mcp server list
openmcp mcp session connect --id <serverId>
openmcp mcp session current

Read the full file on GitHub · 187 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 215 B

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.

2mo ago First seen · 187 lines · 80 tokens per session scan A e23aefbce575

Subscribe to this mod's changes

agent-ruler-openmcp is a skill published in the GitHub repository LSTM-Kirigaya/openmcp-client (750 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,208 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agents LLM ai-agent mcp

agent-ruler-openmcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-ruler-openmcpLSTM-Kirigaya/openmcp-client	Skill	750	5mo ago	Apache-2.0	A	80	Codex
subagent-driven-developmentNousResearch/hermes-agent	Skill	262k	today	MIT	A	17	Claude Code, Codex
mcporterNousResearch/hermes-agent	Skill	262k	today	MIT	A	16	Claude Code, Codex
article-writingaffaan-m/ECC	Skill	299k	yesterday	MIT	A	57	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	yesterday	Apache-2.0	A	217	Claude Code, Codex
safe-refactorJuliusBrussee/caveman	Skill	118k	today	Apache-2.0	A	29	Claude Code, Codex
create-tech-designhumanlayer/humanlayer	Skill	13k	2d ago	Apache-2.0	A	16	Claude Code, Codex