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.
npx agentmods add instructions/vitorbari/mcp-operator/claude-mdgit clone --depth 1 https://github.com/vitorbari/mcp-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/instructions/vitorbari/mcp-operator/claude-md)<a href="https://agentmods.dev/instructions/vitorbari/mcp-operator/claude-md"><img src="https://agentmods.dev/badge/instructions/vitorbari/mcp-operator/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02573 | $0.02573 |
| Opus 5 | $0.01287 | $0.01287 |
| Sonnet 5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
mcp-operator CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
VERSION=$(curl -s https://api.github.com/repos/vitorbari/mcp-operator/releases | jq -r '.[0].tag_name') How it starts
The opening of the file, as written. The whole thing — 336 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.
Development Commands
Building and Testing
# Run comprehensive test suite with envtest
make test
# Run specific controller tests
go test ./internal/controller -v -run "TestMCPServer"
# Run tests for a specific component (e.g., transport)
go test ./pkg/transport -v
# Run E2E tests with Kind cluster
make test-e2e
# Build the operator binary
make build
# Run locally for development (requires CRDs installed)
make run
Code Generation and Manifests
# Generate CRDs, RBAC, and webhooks after API changes
make manifests
# Generate deepcopy methods after API changes
make generate
# Install/uninstall CRDs in cluster
make install
make uninstall
# Deploy/undeploy operator to cluster
make deploy IMG=controller:latest
make undeploy
Linting and Quality
# Run golangci-lint
make lint
# Auto-fix linting issues
make lint-fix
# Format code
make fmt
# Vet code
make vet
Container and Distribution
# Build and push container image
make docker-build IMG=myregistry/mcp-operator:tag
make docker-push IMG=myregistry/mcp-operator:tag
# Build multi-platform images
make docker-buildx IMG=myregistry/mcp-operator:tag
# Generate consolidated install.yaml
make build-installer IMG=myregistry/mcp-operator:tag
Architecture Overview
This is a Kubernetes operator for managing Model Context Protocol (MCP) servers. The architecture follows standard controller-runtime patterns with sophisticated transport abstraction.
Core Components
API Layer (api/v1/mcpserver_types.go)
MCPServerCRD with comprehensive configuration options- Transport-specific configuration (HTTP/Custom)
- Enterprise features: HPA, ingress, RBAC, security contexts
- Rich status reporting with phase tracking and conditions
Controller (internal/controller/mcpserver_controller.go)
MCPServerReconcilerimplements reconciliation loop- Transport-aware resource management via Strategy pattern
- Retry logic with
client-go/util/retry.RetryOnConflictfor optimistic concurrency - Comprehensive status updates with condition management
- Resource ownership and finalizer-based cleanup
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.
- 5d ago First seen · 336 lines · 2,573 tokens per session scan A af3b64b90029
mcp-operator CLAUDE.md is an instructions file published in the GitHub repository vitorbari/mcp-operator (29 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 2,573 tokens to every session, about $0.0129 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
arcade-mcp CLAUDE.md
Claude Code instructions for ArcadeAI/arcade-mcp, covering claude.md, what this is, commands, library dependency graph and versioning rules.
registry copilot-instructions.md
Copilot instructions for modelcontextprotocol/registry, covering copilot instructions for mcp registry, important: publishing mcp servers and development.
registry CLAUDE.md
Claude Code instructions for modelcontextprotocol/registry, covering claude.md and important: publishing mcp servers.
everything-ai-coding AGENTS.md
Instructions for zgsm-ai/everything-ai-coding, covering agents.md, project context, do not commit openspec/, test files and commit conventions.
tailscale-mcp AGENTS.md
AGENTS.md instructions for HexSleeves/tailscale-mcp, covering skill routing and gbrain configuration (configured by /setup-gbrain).
daz-mcp-server CLAUDE.md
Claude Code instructions for bluemoonfoundry/daz-mcp-server, covering claude.md (project index), primary commands, skill modules (reference with @), architecture summary and render api (dazscriptserver native endpoints).