What is cyberquant-mcp CLAUDE.md?

Project instructions for cyberquant-mcp, a TypeScript MCP server that lets AI models access data through an API gateway. They describe the architecture, commands, files, response format, limits, retries, and logging rules.

Use them when developing or debugging the server, its data-query tools, resources, configuration, builds, or API-gateway behavior.

They prevent common integration errors, such as writing logs to the channel used for tool communication, exceeding page limits, or handling pagination and retries incorrectly.

How slb-cn/cyberquant-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to slb-cn/cyberquant-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/slb-cn/cyberquant-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/slb-cn/cyberquant-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/slb-cn/cyberquant-mcp/claude-md.svg)](https://agentmods.dev/instructions/slb-cn/cyberquant-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/slb-cn/cyberquant-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/slb-cn/cyberquant-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 543 This file is loaded in full into every session.

When invoked 543 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00543	$0.00543
Opus 5	$0.00271	$0.00271
Sonnet 5	$0.00109	$0.00109
Haiku 4.5	$0.00054	$0.00054

Measured 5d ago against content hash c045b9ea599c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cyberquant-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 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.

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 · 48 lines

What it actually says

CLAUDE.md

项目定位

cyberquant-mcp 是数据共享平台的 MCP Server，作为 API Gateway 的客户端，通过 stdio 向 AI 模型暴露数据访问能力。

架构：AI 客户端 → MCP Server (本项目) → API Gateway

技术栈

TypeScript (ESM) + Node.js >= 20 + @modelcontextprotocol/sdk + zod + tsup + pnpm

常用命令

pnpm install          # 安装依赖
pnpm build            # tsup 构建 → dist/
pnpm dev              # tsx 开发运行

关键约束

日志只能写 stderr — stdout 用于 MCP stdio 通信，绝对不能污染
所有 API 请求必须带 X-Client-Type: mcp header
pageSize 上限 1000 — 超过时不发请求，直接返回警告提示
CSV 格式返回数据 — 表头取首条数据字段名，节省 token
不自动翻页 — hasMore 时用自然语言引导 AI 缩小查询范围，不暴露 cursor
自然语言引导 — 所有返回（数据、错误、警告）均附带清晰提示
无第三方 HTTP 库 — 使用 Node 20+ 原生 fetch
重试：仅 429/503，最多 3 次，尊重 Retry-After，指数退避上限 10s
与 cyberquant-cli 共用配置 — ~/.cyberquant/config.json，MCP 从 mcp 字段读取专有配置

仓库结构

src/
├── index.ts              # stdio 入口
├── server.ts             # MCP 服务器（注册 Tools + Resources）
├── tools/query.ts        # query_data — CSV 数据查询
├── tools/list.ts         # list_routes — 路由列表
├── tools/clear-routes-cache.ts  # clear_routes_cache — 清除路由元数据缓存
├── resources/            # user-profile / routes
├── lib/api-client.ts     # API Gateway HTTP 客户端（含重试+超时）
├── lib/config.ts         # 配置管理
├── lib/errors.ts         # 错误类型
└── types/index.ts        # 类型定义

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.

5d ago First seen · 48 lines · 543 tokens per session scan A c045b9ea599c

Subscribe to this mod's changes

cyberquant-mcp CLAUDE.md is an instructions file published in the GitHub repository slb-cn/cyberquant-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 543 tokens to every session, about $0.0027 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.

Building agents

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 · 5,182 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

cyberquant-mcp: Instructions file for Claude Code