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.
git clone --depth 1 https://github.com/opendatahub-io/opendatahub-operatorWrote 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.
[](https://agentmods.dev/mcp/opendatahub-io/opendatahub-operator/openshift)<a href="https://agentmods.dev/mcp/opendatahub-io/opendatahub-operator/openshift"><img src="https://agentmods.dev/badge/mcp/opendatahub-io/opendatahub-operator/openshift/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.
<a href="https://agentmods.dev/mcp/opendatahub-io/opendatahub-operator/openshift"><img src="https://agentmods.dev/badge/mcp/opendatahub-io/opendatahub-operator/openshift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
openshift 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 6d 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.
What it actually says
{
"openshift": {
"command": "npx",
"args": [
"-y",
"[email protected]",
"--read-only",
"--toolsets",
"core"
]
}
}What else .mcp.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 6d ago First seen · 12 lines scan A 40aeba550277
openshift is an MCP server published in the GitHub repository opendatahub-io/opendatahub-operator (109 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-09-03.
Other mcp servers, from other repositories
fly-io
MCP server for managing Fly.io machines, apps, logs, and Docker images. Runs locally from the fly-io-mcp-server npm package. Needs 5 environment variables to run.
Komodo MCP Server
MCP server "Komodo MCP Server" as configured in MP-Tool/komodo-mcp-server. Runs in Docker (KOMODO_URL=https://komodo.example.com:9120).
scalingo
Manage Scalingo PaaS apps, deployments, containers, logs and env vars from your AI assistant. Remote server at scalingo.usefulapi.io.
proxmox
MCP server "proxmox" as configured in dallaswk/proxmox-ai. Launched with /opt/proxmox-ai/.venv/bin/proxmox-ai. Needs 7 environment variables to run.
kubernetes-readonly-mcp
A read-only Kubernetes MCP server for safely interacting with Kubernetes clusters. Runs locally from the kubernetes-readonly-mcp Python package.
ovh-api-mcp
MCP server "ovh-api-mcp" as configured in davidlandais/ovh-api-mcp. Runs in Docker (ghcr.io/davidlandais/ovh-api-mcp:0.3.0). Needs 7 environment variables to run.