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 rules/csmar432/finai-research/mcp_toolsgit clone --depth 1 https://github.com/csmar432/finai-researchWrote 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/rules/csmar432/finai-research/mcp_tools)<a href="https://agentmods.dev/rules/csmar432/finai-research/mcp_tools"><img src="https://agentmods.dev/badge/rules/csmar432/finai-research/mcp_tools.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 5.1 | $0.02955 | $0.02955 |
| Opus 5 | $0.01477 | $0.01477 |
| Sonnet 5 | $0.00591 | $0.00591 |
| Haiku 4.5 | $0.00296 | $0.00296 |
Grade A, and why
mcp_tools 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP工具配置与使用指南
快速导航
| 你想要... | 使用这个工具 |
|---|---|
| 搜学术论文（全文） | user-openalex、user-arxiv、user-context7、user-semantic-scholar |
| 查A股行情/财务 | user-tushare（需Token）或 akshare（免费备选） |
| 查A股财务（免费） | user-yfinance（中概股/港股ADR） |
| 查宏观指标（GDP/CPI/M2） | user-financial（免费akshare+WorldBank） |
| 查美国国债收益率/经济日历 | user-eodhd（需Key）或 user-fed-data（免费） |
| 读研报、看新闻、找分析师 | user-eastmoney-reports（免费） |
| 查外汇/大宗商品/航运 | user-enhanced-finance（免费） |
| SEC年报/10-K/8-K | user-sec-edgar（免费） |
| 美股行情/财务/期权/ETF | user-yfinance（免费） |
| 网络搜索（中英文） | user-brave-search（需Key）或 WebSearch |
| 中国省级/市级统计 | user-province-stats、user-hubei-stats |
核心原则：每个数据需求都有四层fallback，确保任何情况下都能获取数据。
MCP服务概览（43个目录服务器）
学术文献（5个）
| 服务 | 功能 | API Key |
|---|---|---|
user-openalex |
OpenAlex论文元数据（2亿+，免费） | 无需 |
user-arxiv |
ArXiv论文搜索（免费） | 无需 |
user-context7 |
论文全文索引（免费） | 无需 |
user-semantic-scholar |
Semantic Scholar（需Key可选） | 免费层够用 |
user-nber-wp |
NBER工作论文（免费） | 无需 |
A股数据（4个）
| 服务 | 功能 | API Key | 免费备选 |
|---|---|---|---|
user-tushare |
A股财务/行情/融资融券 | TUSHARE_TOKEN | akshare / baostock |
user-eastmoney-reports |
研报/新闻/概念/分析师 | 无需 | — |
user-wind |
Wind数据 | 无Key（需Wind账号） | akshare |
user-csmar |
CSMAR国泰安 | CSMAR_API_KEY（机构） | akshare |
美股/全球市场（3个）
| 服务 | 功能 | API Key |
|---|---|---|
user-yfinance |
美股/港股行情/财务/期权/ETF | 无需 |
user-sec-edgar |
SEC 10-K/10-Q/8-K公告 | 无需 |
user-enhanced-finance |
外汇/航运指数/白银/期货 | 无需 |
宏观经济（10个）
| 服务 | 功能 | API Key |
|---|---|---|
user-financial |
中国宏观（GDP/CPI/M2/EPU，akshare+WorldBank） | 无需 |
user-eodhd |
国债收益率/经济日历 | EODHD_API_KEY |
user-fed-data |
美联储/FOMC数据 | 无需 |
user-wb-data |
世界银行宏观指标 | 无需 |
user-imf-data |
IMF世界经济展望 | 无需 |
user-oecd-data |
OECD经济数据 | 无需 |
user-bea-data |
美国经济分析局GDP | 无需 |
user-macro-ceic |
CEIC中国宏观 | 无需 |
user-macro-datas |
宏观数据聚合 | 无需 |
user-macro-stats |
宏观统计 | 无需 |
工具类（10个）
| 服务 | 功能 |
|---|---|
user-brave-search |
网络搜索（中英文，需Key） |
user-latex-mcp |
LaTeX排版检查 |
user-pandas-mcp |
数据处理（pandas） |
user-playwright-mcp |
浏览器自动化 |
user-e2b-mcp |
云端代码执行 |
user-filesystem-mcp |
文件系统操作 |
user-province-stats |
中国省级统计 |
user-hubei-stats |
湖北省统计 |
user-wuhan-stats |
武汉市统计 |
user-cryptocompare |
加密货币（BTC/ETH等） |
user-newsapi |
全球财经新闻（需Key） |
user-eastmoney-fund |
公募基金数据 |
user-eastmoney-bond |
债券数据 |
user-eastmoney-option |
期权数据 |
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.
- 6d ago First seen · 348 lines · 2,955 tokens per session scan A 53df2a3ddbed
mcp_tools is a cursor rule published in the GitHub repository csmar432/finai-research (112 stars, last pushed yesterday), licensed MIT. It adds 2,955 tokens to every session, about $0.0148 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 2026-08-30.
Other cursor rules, from other repositories
02-data-models
Activo en archivos de modelos Pydantic. Gobernanza FINOS CDM: inmutabilidad, linaje, precisión financiera.
cur-focus-data-engineer
Builds reliable ingest and transformation pipelines for AWS CUR 2.0, Azure Cost Management exports, GCP billing export, and the FOCUS specification. Turns raw vendor exports into a trusted cost warehouse.
ml-workload-cost-optimizer
Specialist in ML training and inference cost -- GPU selection, spot strategies, multi-region training, inference optimization via quantization and batching, and managed-service tradeoffs (SageMaker / Vertex AI / Azure ML).
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.