What is zihin-mcp CLAUDE.md?

Project instructions for the Zihin MCP server package, a local proxy that connects MCP clients such as Codex or Claude Code to a production server over HTTP.

Use them when developing, testing, running, or documenting the @zihin/mcp-server package and its local proxy.

They explain the project structure, commands, authentication, testing requirements, and language and commit conventions in one place.

How zihin-ai/zihin-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zihin-ai/zihin-mcp. 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/zihin-ai/zihin-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/zihin-ai/zihin-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zihin-ai/zihin-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/zihin-ai/zihin-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zihin-ai/zihin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zihin-ai/zihin-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/zihin-ai/zihin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zihin-ai/zihin-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,709 This file is loaded in full into every session.

When invoked 1,709 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.

Model	Per session	Once invoked
Fable 5.1	$0.01709	$0.01709
Opus 5	$0.00855	$0.00855
Sonnet 5	$0.00342	$0.00342
Haiku 4.5	$0.00171	$0.00171

Measured 7d ago against content hash 44f19917672b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zihin-mcp 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 7d 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 · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — @zihin/mcp-server

O que e este projeto

Pacote npm @zihin/mcp-server — proxy stdio-to-HTTP que conecta clientes MCP (Claude Desktop, Cursor, Claude Code, Codex, Windsurf) ao Zihin MCP Server em producao.

Arquitetura

Cliente MCP <-stdio-> [Proxy local (src/index.js)] <-HTTP-> https://llm.zihin.ai/mcp

src/index.js — proxy principal (~670 linhas), exporta startProxy(), os classificadores de erro (isAuthError/isConnectionError/isProtocolVersionError/isInputRequiredError/isTimeoutError) e resolveCallTimeoutMs()
src/install-skills.js — subcomando install-skills (skills no formato nativo de cada client)
bin/zihin-mcp.js — CLI entry point
Usa MCP SDK v2: Client + StreamableHTTPClientTransport (@modelcontextprotocol/client) e Server low-level + StdioServerTransport (@modelcontextprotocol/server)
Auth via header X-Api-Key, RBAC enforced server-side

Comandos

# Rodar testes (requer API Key valida)
ZIHIN_API_KEY=zhn_live_xxx npm test

# Rodar o proxy localmente
ZIHIN_API_KEY=zhn_live_xxx node bin/zihin-mcp.js

# Ressincronizar as skills empacotadas com o BE (passo de release)
npm run sync-skills                              # do checkout irmao ../zihin-agent-builder
ZIHIN_API_KEY=zhn_live_xxx npm run sync-skills -- --from-server

Convencoes

Idioma: portugues brasileiro para docs, commits e comentarios
Formato de commit: feat(scope): descricao com Co-Authored-By: Claude <modelo> <[email protected]>
Sem emojis
JS puro, ESM (type: module), Node.js >= 20 (exigido pelo SDK v2)
Zero devDependencies — testes usam node:test nativo
Dependencias: @modelcontextprotocol/client + @modelcontextprotocol/server (SDK v2, pacotes divididos)

Estrutura

zihin-mcp/
├── package.json
├── bin/zihin-mcp.js       <- CLI entry point
├── src/index.js           <- Proxy stdio-to-HTTP
├── src/install-skills.js  <- Subcomando install-skills
├── scripts/sync-skills.mjs <- Ressincroniza plugin/skills/ com o BE (release)
├── test/proxy.test.js     <- Integracao real contra producao (requer key)
├── test/error-classification.test.js  <- Unit, sem rede
├── test/install-skills.test.js        <- Unit + e2e local, sem rede
├── plugin/                <- Plugin Claude Code (skills empacotadas)
├── .github/workflows/
│   ├── ci.yml             <- Testes OFFLINE em push/PR (sem key — nao queima turno de agente)
│   └── publish.yml        <- Gate de integracao real (REQUIRE_INTEGRATION=1) em tag v*; publish e no-op se a versao ja esta no npm
├── README.md
├── CHANGELOG.md
├── LICENSE (MIT)
├── .gitignore
└── .npmignore

Read the full file on GitHub · 113 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.

7d ago Changed · +21 lines · +529 tokens per session 44f19917672b
11d ago First seen · 92 lines · 1,180 tokens per session scan A 5565cdc5672c

Subscribe to this mod's changes

zihin-mcp CLAUDE.md is an instructions file published in the GitHub repository zihin-ai/zihin-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 1,709 tokens to every session, about $0.0085 per session on Opus 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

zihin-mcp: Instructions file for Claude Code