mcp-server-openshift: Instructions file for Claude Code

CLAUDE.md

mcp-server-openshift CLAUDE.md is an instructions file for Claude Code from sanjaypsachdev/mcp-server-openshift. It costs 1,022 tokens per session, scanned A, original, MIT.

Repository instructions for an OpenShift MCP server, a program that lets an agent work with OpenShift through defined tools and resources. They cover how to build, run, test, and lint the server.

In plain words
What is it for?
Use them when developing or maintaining the server, running its tests, checking lint, or starting its standard and HTTP modes.
Why use it?
They give contributors the commands and architecture needed to change the server safely. This avoids guessing how its tools, resources, and prompts are wired together.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is sanjaypsachdev/mcp-server-openshift's own configuration. It tells Claude Code how to work on mcp-server-openshift itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-server-openshift configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sanjaypsachdev/mcp-server-openshift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sanjaypsachdev/mcp-server-openshift/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sanjaypsachdev/mcp-server-openshift

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-server-openshift CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sanjaypsachdev/mcp-server-openshift/claude-md/github.svg)](https://agentmods.dev/instructions/sanjaypsachdev/mcp-server-openshift/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sanjaypsachdev/mcp-server-openshift/claude-md"><img src="https://agentmods.dev/badge/instructions/sanjaypsachdev/mcp-server-openshift/claude-md/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.

agentmods 80×15 button for mcp-server-openshift CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sanjaypsachdev/mcp-server-openshift/claude-md"><img src="https://agentmods.dev/badge/instructions/sanjaypsachdev/mcp-server-openshift/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,022 This file is loaded in full into every session.
When invoked 1,022 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01022 $0.01022
Opus 5.5 $0.00409 $0.00409
Sonnet 5.5 $0.00204 $0.00204
Haiku 4.5 $0.00102 $0.00102

Measured 2mo ago against content hash e3e62f0c7c5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server-openshift 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 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.

CLAUDE.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

# Build
npm run build          # tsc compile to dist/

# Development (no compile step)
npm run dev            # tsx src/index.ts (stdio)
npm run dev:http       # tsx src/index.ts --http (SSE on :3000)

# Run the server
npm run start          # dist/index.js (stdio, default)
npm run start:sse      # dist/index.js --sse --port=3000

# Test
npm test               # vitest (run once)
npm run test:watch     # vitest --watch
npm run test:coverage  # vitest --coverage (requires ≥80% on all metrics)

# Single test file
npx vitest run tests/oc-login.test.ts

# Lint
npm run lint           # eslint src/
npm run lint:fix       # eslint src/ --fix

Architecture

MCP server structure

src/index.ts is the single entry point. It creates OpenShiftMCPServer, which wires together all four MCP capability types:

  • Tools — 14 oc_* tools registered in index.ts, each in src/tools/oc-*.ts
  • Resources — 3 static read-only resources in src/resources/
    • openshift://cluster-info, openshift://project-list, openshift://app-templates
  • Prompts — 2 prompt templates in src/prompts/
  • Sampling — pod-log sampling handler in src/sampling/pod-logs.ts

Transport is auto-detected: stdio by default; HTTP/SSE when --http, --sse, --port=N, or MCP_TRANSPORT=sse/http is set.

Runtime environment variables: OPENSHIFT_CONTEXT, OPENSHIFT_NAMESPACE (cluster defaults), MCP_TRANSPORT, MCP_PORT, MCP_HOST (server config).

Note: src/tools/oc-status.ts exists as a reference implementation showing the full tool utility pattern but is intentionally not registered in index.ts.

Tool pattern

Every tool file exports two things:

  1. A Tool object (the MCP tool definition with name, description, inputSchema)
  2. A handle* async function that takes typed args and returns an MCP content response

Input validation uses Zod schemas defined in src/models/tool-models.ts. All schemas and their inferred TypeScript types live there; individual tool files import from it. OcRolloutSchema and OcStartBuildSchema are defined there but have no corresponding tool files yet — stubs for planned tools.

Read the full file on GitHub · 80 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. 2mo ago First seen · 80 lines · 1,022 tokens per session scan A e3e62f0c7c5d

Subscribe to this mod's changes

mcp-server-openshift CLAUDE.md is an instructions file published in the GitHub repository sanjaypsachdev/mcp-server-openshift (1 stars, last pushed 10d ago), licensed MIT. It adds 1,022 tokens to every session, about $0.0041 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 2026-08-31.

Related

mcp-server-openshift CLAUDE.md compared with instructions from other repositories

mcp-server-openshift CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-server-openshift CLAUDE.mdsanjaypsachdev/mcp-server-openshiftInstructions file110d agoMITA1,022Claude Code
plan-forge dapr.instructions.mdsrnichols/plan-forgeInstructions file62d agoMITA4,975GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot