Borrowing it
Nothing to install: this file belongs to Lumina-AI-studio/mcp-production-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lumina-AI-studio/mcp-production-kit/main/CLAUDE.mdgit clone --depth 1 https://github.com/Lumina-AI-studio/mcp-production-kitWrote 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/lumina-ai-studio/mcp-production-kit/claude-md)<a href="https://agentmods.dev/instructions/lumina-ai-studio/mcp-production-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/lumina-ai-studio/mcp-production-kit/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.
<a href="https://agentmods.dev/instructions/lumina-ai-studio/mcp-production-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/lumina-ai-studio/mcp-production-kit/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00322 | $0.00322 |
| Opus 5.5 | $0.00129 | $0.00129 |
| Sonnet 5.5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
mcp-production-kit 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.
What it actually says
mcp-production-kit — production-ready TypeScript MCP server template
What this is
Clone-and-adapt remote MCP server: Streamable HTTP, OAuth 2.1 resource server, per-tool RBAC, append-only audit logging, rate limits, tests, EU (Hetzner) deployment. MIT.
Hard rules
- This is a TEMPLATE, not a platform: no gateway, no multi-tenancy, no billing, no hosted mode. Reject scope in that direction.
- Tools are task-oriented verbs with zod schemas; read-only by default; write tools require explicit scope + confirmation payload.
- Every tool call MUST produce an audit event (actor, tool, args hash, status, latency, trace id). Audit sink is append-only.
- Deny-by-default RBAC. Never ship a tool without a scope mapping.
- Follow the CURRENT MCP spec — verify auth flow details against the official docs before changing src/auth (spec moves fast).
Stack & commands
- Node 22, ESM, strict TS, zod; @modelcontextprotocol/sdk (official).
- vitest; MCP Inspector scripts in /test/inspector.
pnpm build/pnpm test/pnpm lintgreen before commit.pnpm example:upboots the Nordwind demo (Keycloak + Postgres) + server.
Testing
- Every auth change needs a negative test (wrong scope → 403 path).
- Every new tool needs: schema test, audit-event test, eval case.
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 · 27 lines · 322 tokens per session scan A 713447e0a9bc
mcp-production-kit CLAUDE.md is an instructions file published in the GitHub repository Lumina-AI-studio/mcp-production-kit (0 stars, last pushed 3mo ago), licensed MIT. It adds 322 tokens to every session, about $0.0013 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.
mcp-production-kit CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-production-kit CLAUDE.mdLumina-AI-studio/mcp-production-kit | Instructions file | 0 | 3mo ago | MIT | A | 322 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |