Amazingdata Mcp

Community

infometa

amazingdata-mcp

星耀数智 AmazingData 金融数据 MCP 连接器使用说明。涵盖 57 个工具：A股/ETF/期权/期货/可转债行情与K线、财务三表、股东结构、两融、龙虎榜、指数成分、国债收益率等。连接器已配置用户凭证（AD_USERNAME/AD_PASSWORD/AD_HOST/AD_PORT 环境变量注入，启动时自动登录）。

Overview

Publisher	infometa
Repository	`workbuddyskills`
Skill name	`amazingdata-mcp`
Stars	376
Forks	124
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by infometa on GitHub. Read the source before you install it.

Installation

Install the Amazingdata Mcp AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/infometa/workbuddyskills/tree/main/connectors/amazingdata-mcp/skills/amazingdata
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/infometa/workbuddyskills/tree/main/connectors/amazingdata-mcp/skills/amazingdata

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/infometa/workbuddyskills.git /tmp/workbuddyskills
mkdir -p .claude/skills
cp -r /tmp/workbuddyskills/connectors/amazingdata-mcp/skills/amazingdata .claude/skills/amazingdata-mcp

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Amazingdata Mcp in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Amazingdata Mcp on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Amazingdata Mcp is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

星耀数智 AmazingData MCP 使用说明

连接与认证

连接器以 stdio 模式启动，启动时读取环境变量 AD_USERNAME、AD_PASSWORD、AD_HOST、AD_PORT 自动登录星耀数智数据服务。
连接表单中填写用户名、密码及服务器地址/端口（开户时由星耀数智下发，请向用户确认后如实填写）。
首次连接较慢属正常：启动脚本会自动下载并安装运行依赖（需 3~5 分钟）。若用户反馈"工具找不到/连接失败"，很可能是首次安装尚未完成——请告知用户等待 5 分钟后重试，或重启 WorkBuddy 再连接（第二次会秒连，依赖已缓存）。
若启动时登录失败（凭证缺失或网络异常），服务仍可用：先调用 mcp_get_login_status 检查状态，必要时用 mcp_login 显式登录。

通用约定（所有数据工具均遵循）

日期格式：8 位整数 YYYYMMDD，如 20240101；begin_date 默认 19900101，end_date 默认当天。
证券代码：代码.交易所后缀，如 000001.SZ、600000.SH、510300.SH（ETF）、可转债如 113050.SH。
K线周期 period：min1、min3、min5、min10、min15、min30、min60、min120、day、week、month、season、year（共 13 种，对应手册附录 Period 枚举）。
建议限制：单次日期范围不超过 1 年；单次代码数量不超过 50 个。
行情惯例：涨跌颜色遵循 A 股惯例（涨红跌绿）。

工具目录

登录管理

工具	用途
`mcp_get_login_status`	查询当前登录状态（无参数，诊断首选）
`mcp_login`	显式登录，可不传参（用环境变量凭证）或传 username/password/host/port

证券代码与交易日历

工具	关键参数
`mcp_code_info(security_type)`	证券代码信息，默认 `EXTRA_STOCK_A`
`mcp_code_list(security_type)`	证券代码列表
`mcp_code_list_future(security_type)`	期货代码，默认 `EXTRA_FUTURE`
`mcp_code_list_option(security_type)`	期权代码，默认 `EXTRA_OPTION`
`mcp_history_code_list(security_type, date)`	某历史日期的代码列表
`mcp_bj_code_mapping()`	北交所代码映射
`mcp_calendar(market, date)`	交易日历，market 为 `SH`/`SZ` 等；注意不接受 begin_date/end_date

行情数据

工具	关键参数
`mcp_kline(code_list, begin_date, end_date, period)`	K 线；`count` 可选；period 见通用约定
`mcp_snapshot(code_list, asset_type)`	实时快照，asset_type 默认 `auto`
`mcp_industry_index_quote(index_code_list, begin_date, end_date)`	行业指数行情
`mcp_treasury_yield(code_list, begin_date, end_date)`	国债收益率

财务报表

工具	说明
`mcp_balance_sheet(code_list, statement_type, begin_date, end_date)`	资产负债表
`mcp_cash_flow(code_list, statement_type, ...)`	现金流量表
`mcp_income(code_list, statement_type, ...)`	利润表
`mcp_profit_express(code_list, begin_date, end_date)`	业绩快报
`mcp_profit_notice(code_list, ...)`	业绩预告

statement_type 不传时返回全部报告期口径。

公司与股东

工具	用途
`mcp_stock_basic(code_list, summary_only)`	基础资料，summary_only 精简
`mcp_history_stock_status(code_list, begin_date, end_date)`	历史 ST/退市等股状态
`mcp_share_holder(code_list, begin_date, end_date)`	股东
`mcp_holder_num(code_list, begin_date, end_date)`	股东户数
`mcp_equity_structure(code_list, begin_date, end_date)`	股本结构
`mcp_equity_pledge_freeze(code_list, begin_date, end_date)`	股权质押冻结
`mcp_equity_restricted(code_list, begin_date, end_date)`	限售股
`mcp_dividend(code_list, begin_date, end_date)`	分红
`mcp_right_issue(code_list, begin_date, end_date)`	配股

两融与资金

工具	用途
`mcp_margin_summary(begin_date, end_date)`	两融汇总，仅需日期
`mcp_margin_detail(code_list, begin_date, end_date)`	两融明细
`mcp_long_hu_bang(code_list, begin_date, end_date)`	龙虎榜
`mcp_block_trading(code_list, begin_date, end_date)`	大宗交易

指数

工具	用途
`mcp_index_constituent(index_code, date)`	指数成分股
`mcp_index_constituent_weight(index_code, date)`	指数成分权重
`mcp_industry_index_info(index_type)`	行业指数目录，默认 `SW` 申万
`mcp_industry_index_constituent(index_code, date)`	行业指数成分股
`mcp_industry_index_weight(index_code, date)`	行业指数成分权重

ETF

工具	用途
`mcp_etf_purchase_redemption(code_list, date)`	申赎清单
`mcp_etf_fund_share(code_list, begin_date, end_date)`	基金份额
`mcp_etf_iopv(code_list, begin_date, end_date)`	IOPV 净值估算

期权

工具	用途
`mcp_option_basic_info(code_list)`	期权基本资料
`mcp_option_contract_info(code_list)`	期权合约信息
`mcp_option_month_contract_change(code_list, begin_date, end_date)`	期权月度合约变化

可转债

工具	用途
`mcp_kzz()`	可转债概况
`mcp_convertible_bond_issue(code_list, begin_date, end_date)`	发行
`mcp_convertible_bond_balance(code_list, begin_date, end_date)`	余额
`mcp_convertible_bond_conversion(code_list)`	转股情况
`mcp_convertible_bond_conversion_change(code_list, begin_date, end_date)`	转股变化
`mcp_convertible_bond_adjustment(code_list, begin_date, end_date)`	条款调整
`mcp_convertible_bond_redemption(code_list)`	强赎
`mcp_convertible_bond_resale(code_list)`	回售
`mcp_convertible_bond_terms(code_list)`	条款
`mcp_convertible_bond_resale_notice(code_list, begin_date, end_date)`	回售提示
`mcp_convertible_bond_redemption_notice(code_list, begin_date, end_date)`	强赎提示
`mcp_convertible_bond_suspension(code_list, begin_date, end_date)`	停复牌

其他

工具	用途
`mcp_backward_factor(code_list)`	后复权因子
`mcp_search_manual(keyword, max_chars)`	检索开发手册，不确定接口用法时先用它

Resources

资源	用途
`amazingdata://doc/manual`	开发手册目录
`amazingdata://doc/api-summary`	接口摘要

典型调用示例


1. 查 K 线：
   mcp_kline(code_list=["600519.SH"], begin_date=20240601, end_date=20240901, period="day")

2. 查利润表：
   mcp_income(code_list=["600036.SH"], begin_date=20240101, end_date=20241231)

3. 查指数成分：
   mcp_index_constituent(index_code="000300.SH", date=20240901)

错误处理

所有工具返回带 success 字段的 dict。失败时关注 error_type：

not_logged_in → 调 mcp_get_login_status，再 mcp_login；
invalid_parameter → 检查日期为 8 位整数、代码带交易所后缀；
connection_error / query_failed → 缩短日期范围、减少代码数量、稍后重试。

Frequently asked questions

What does the Amazingdata Mcp AI skill do?

Why use Amazingdata Mcp on TypingMind?

Because you install it once and use it with any model. Amazingdata Mcp is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Amazingdata Mcp in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/infometa/workbuddyskills/tree/main/connectors/amazingdata-mcp/skills/amazingdata. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Amazingdata Mcp?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Amazingdata Mcp?

As many as you like. As long as a model supports skills, you can use Amazingdata Mcp with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Amazingdata Mcp AI skill free?

It is published on GitHub by infometa. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Benchmark Methodology

affaan-m

CommunityPopular

Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence,…

Investor Materials

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections,…

Evm

Read-only EVM client: wallets, tokens, gas across 8 chains.

Excel Author

Build auditable financial workbooks headless via openpyxl.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

星耀数智 AmazingData MCP 使用说明

连接与认证

通用约定（所有数据工具均遵循）

工具目录

登录管理

证券代码与交易日历

行情数据

财务报表

公司与股东

两融与资金

指数

ETF

期权

可转债

其他

Resources

典型调用示例

错误处理

Frequently asked questions

Related AI Skills

Set up your own AI workspace now