Alpha Desk Investment Research
JingHao-Leon/dsh-alpha-desk
Runs an AI investment research desk around the aihf hedge-fund CLI, with research cycles, backtests and iFinD data, under a risk gate and a rule against placing real trades.
Queries historical A-share, Hong Kong stock, ETF and index data through an MCP server: daily K-lines, financial statements, market indicators and screening.
Install Stock Market Data MCP Query
$ npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Yourdaylight/stock_datasource stock-mcp-query --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Yourdaylight/stock_datasource.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/stock-mcp-query .claude/skills/stock-mcp-query && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "stock-mcp-query" agent skill from https://github.com/Yourdaylight/stock_datasource/tree/main/skills/stock-mcp-query into .claude/skills/stock-mcp-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stock-mcp-query", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Yourdaylight/stock_datasource/tree/main/skills/stock-mcp-queryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Yourdaylight/stock_datasource stock-mcp-query --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yourdaylight/stock_datasource.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/stock-mcp-query .agents/skills/stock-mcp-query && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "stock-mcp-query" agent skill from https://github.com/Yourdaylight/stock_datasource/tree/main/skills/stock-mcp-query into .agents/skills/stock-mcp-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stock-mcp-query", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Yourdaylight/stock_datasource stock-mcp-query --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yourdaylight/stock_datasource.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/stock-mcp-query .cursor/skills/stock-mcp-query && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "stock-mcp-query" agent skill from https://github.com/Yourdaylight/stock_datasource/tree/main/skills/stock-mcp-query into .cursor/skills/stock-mcp-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stock-mcp-query", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Yourdaylight/stock_datasource.git --path skills/stock-mcp-query--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Yourdaylight/stock_datasource stock-mcp-query --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yourdaylight/stock_datasource.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/stock-mcp-query .gemini/skills/stock-mcp-query && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "stock-mcp-query" agent skill from https://github.com/Yourdaylight/stock_datasource/tree/main/skills/stock-mcp-query into .gemini/skills/stock-mcp-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stock-mcp-query", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Yourdaylight/stock_datasource stock-mcp-queryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Yourdaylight/stock_datasource.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/stock-mcp-query .github/skills/stock-mcp-query && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "stock-mcp-query" agent skill from https://github.com/Yourdaylight/stock_datasource/tree/main/skills/stock-mcp-query into .github/skills/stock-mcp-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stock-mcp-query", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Yourdaylight/stock_datasource stock-mcp-query --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yourdaylight/stock_datasource.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/stock-mcp-query .opencode/skills/stock-mcp-query && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "stock-mcp-query" agent skill from https://github.com/Yourdaylight/stock_datasource/tree/main/skills/stock-mcp-query into .opencode/skills/stock-mcp-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stock-mcp-query", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
stock-mcp-query- GitHub stars
- 189
- Token cost
- ~1.1k tokens
- SKILL.md length
- 439 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Queries historical A-share, Hong Kong stock, ETF and index data through an MCP server: daily K-lines, financial statements, market indicators and screening.
- Works in 2 steps: STOCK_MCP_TOKEN environment variable — a… → STOCK_MCP_SERVER_URL environment…
- Pulling daily K-line data for an A-share, Hong Kong stock, ETF or index
- SKILL.md covers Prerequisites, Setup Check, DeepSeek Harness and MCP Server Configuration…, plus 4 more sections
- Needs STOCK_MCP_TOKEN
What it does
The skill needs a `STOCK_MCP_TOKEN` environment variable, a JWT bought from the management platform, and optionally `STOCK_MCP_SERVER_URL` for the server address. It first checks that the token is set; if not, it walks you through subscribing on the platform's MCP data query page, buying a quota pack, copying the issued token and exporting it. The remote HTTP MCP endpoint on port 8001 requires that token.
Inside DeepSeek Harness the agent does not call the raw plugin tools. It calls `stock_list_tools` with a category such as market, financial, index, etf or hk and a keyword, then `stock_call_tool` with a tool name from that list and JSON arguments matching its input schema. Keep queries narrow, with one code and a short date range, because results are truncated. Other clients such as Claude Code or Cursor add an MCP server entry to their configuration. Data categories include daily K-lines, daily basics, adjustment factors and financial statements.
When your agent uses it
- Pulling daily K-line data for an A-share, Hong Kong stock, ETF or index
- Fetching balance sheet, income or cash flow statements
- Screening or batch-querying market indicators through MCP
Example prompts
- “Get the daily K-line for one A-share over the last month through the stock MCP.”
- “List the financial statement tools available in the stock MCP server.”
- “Fetch the latest market indicators for a Hong Kong stock using stock_list_tools and then stock_call_tool.”
Requirements
- A STOCK_MCP_TOKEN issued by the management platform
- Optionally a STOCK_MCP_SERVER_URL for the MCP server
- An MCP-capable client such as DeepSeek Harness, Claude Code or Cursor
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- STOCK_MCP_TOKEN environment variable — a JWT token purchased from the management platform (nps_enhanced)
- STOCK_MCP_SERVER_URL environment variable (optional) — the MCP server URL, defaults to the URL provided at purchase time
What it can do on your machine
Read from SKILL.md and the folder at commit 3d4dbd2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
STOCK_MCP_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Stock Market Data MCP Query loads about 1.1k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 439 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Yourdaylight/stock_datasource at commit 3d4dbd2, republished under its MIT licence (© Yourdaylight). 439 words, ~1,102 tokens.
Download SKILL.mdSave it as
.claude/skills/stock-mcp-query/SKILL.md (or your agent's skills folder).- name
- stock-mcp-query
- description
- Query historical stock market data (A-shares, HK stocks, ETFs, indices) via MCP. Use when the user wants daily K-line, financial statements, market indicators, screening, or other batch data. DeepSeek Harness clients should call stock_list_tools then stock_call_tool. Remote HTTP MCP on port 8001 still requires STOCK_MCP_TOKEN.
Stock MCP Query
Query historical stock market data including daily OHLCV, financial reports, index data, ETF data, and more through the MCP protocol.
Prerequisites
This skill requires:
- STOCK_MCP_TOKEN environment variable — a JWT token purchased from the management platform (nps_enhanced)
- STOCK_MCP_SERVER_URL environment variable (optional) — the MCP server URL, defaults to the URL provided at purchase time
Setup Check
Before using any data query tools, verify the environment is configured:
# Check if token exists
echo ${STOCK_MCP_TOKEN:+Token is set}${STOCK_MCP_TOKEN:-ERROR: STOCK_MCP_TOKEN not set}If STOCK_MCP_TOKEN is not set:
- Visit the management platform (nps_enhanced web panel)
- Navigate to "MCP Data Query" subscription page
- Purchase a query quota pack (e.g., 10k records for 10 CNY)
- Copy the issued token
- Set the environment variable:
bash export STOCK_MCP_TOKEN="eyJ..." export STOCK_MCP_SERVER_URL="https://your-node:8001/messages"
DeepSeek Harness
When running inside DeepSeek Harness (dsh), do not call the raw plugin tools. Use:
mcp__stock__stock_list_tools—categoryis one ofmarket|basic|financial|index|etf|hk|realtime|toplist|other;queryis a keyword such asdailyor a ts_code prefix.mcp__stock__stock_call_tool—tool_namemust be anamereturned by the list tool (example:tushare_daily_get_daily_data);argumentsis a JSON object matching that tool'sinputSchema.
Keep queries narrow (one ts_code / code and a short date range). Results are truncated.
Start dsh with this repo's overlay instead of pointing at localhost:8001/messages:
export STOCK_DATASOURCE_ROOT=/absolute/path/to/stock_datasource
dsh web --patch "$STOCK_DATASOURCE_ROOT/integrations/dsh/stock.cordis.yml"Stdio MCP spawned by dsh does not use STOCK_MCP_TOKEN.
MCP Server Configuration (Claude Code / Cursor / PicoClaw)
Add to your MCP client configuration:
{
"mcpServers": {
"stock-data": {
"type": "streamable-http",
"url": "${STOCK_MCP_SERVER_URL}",
"headers": {
"Authorization": "Bearer ${STOCK_MCP_TOKEN}"
}
}
}
}Available Data Categories
| Category | Description | Example Tools |
|---|---|---|
| Daily K-line | OHLCV + volume + turnover | tushare_daily_* |
| Daily Basics | PE, PB, market cap, volume ratio | tushare_daily_basic_* |
| Adj Factor | Forward/backward adjustment factors | tushare_adj_factor_* |
| Financial | Balance sheet, income, cash flow | tushare_balancesheet_*, etc. |
| Index | Index daily, weights, components | tushare_index_* |
| ETF | ETF daily prices and holdings | tushare_fund_* |
| HK Stock | Hong Kong stock daily data | akshare_hk_* |
| Market | Market overview, trading calendar | tushare_trade_cal_* |
Show full SKILL.md (159 more words)Show less
Usage Notes
- Each tool call returns data and counts against your query quota
- The response includes
_usage.record_countshowing records returned - The response includes
_usage.quota_remainingshowing remaining quota - When quota is exhausted, purchase additional packs from the management platform
- Data is sourced from ClickHouse and covers the full available history
Billing
- Billed per record (data row) returned by each tool call
- Query packs are valid for 90 days from purchase
- Multiple packs stack additively (quota accumulates)
- Usage is reconciled asynchronously between the MCP server and management platform
Troubleshooting
- 401 "API key required":
STOCK_MCP_TOKENis not set or not passed in Authorization header - 401 "Token expired": Your token has expired. Purchase a new quota pack to get a fresh token
- 401 "Invalid token": Token is malformed or the server's public key doesn't match
- No data returned: Check that the requested date is a trading day, or the stock code is valid
- Quota exhausted: The
_usage.quota_remainingwill show 0. Purchase additional packs
© Yourdaylight, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/stock-mcp-query of Yourdaylight/stock_datasource.
Open the folder on GitHubat commit 3d4dbd2
Compare with similar skills
Stock Market Data MCP Query next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Stock Market Data MCP Query this skillYourdaylight/stock_datasource | 189 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Alpha Desk Investment ResearchJingHao-Leon/dsh-alpha-desk | 181 | — | ~1.3k | Automated safety check: Notes | MIT | |
| Senpi Market PulseSenpi-ai/senpi-skills | 134 | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Vibe-Trading Finance ToolkitHKUDS/Vibe-Trading | 35k | — | ~6.5k | Automated safety check: Pass | MIT | |
| Tradingview MCPatilaahmettaner/tradingview-mcp | 5k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Earnings AnalysisWind-Alice/AliceMarket | 134 | 3 repos | ~2.2k | Automated safety check: Pass | None |
Similar skills
Senpi Market Pulse
Senpi-ai/senpi-skills
Produces a structured cross-asset read of the day across crypto, equities, indices, commodities and macro, using a bundled engine for data and ending with a signals brief.
Vibe-Trading Finance Toolkit
HKUDS/Vibe-Trading
Finance research toolkit with backtesting, factor analysis, a library of prebuilt alphas, options pricing and a Shadow Account loop that tests rules extracted from your trade journal.
Tradingview MCP
atilaahmettaner/tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and…
Earnings Analysis
Wind-Alice/AliceMarket
Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.
Apocdata
ApocData/ApocData-skill
A-share data service with structured announcement parsing: every announcement carries an AI summary, category, importance level and sentiment, fully traceable to source.
More from Yourdaylight/stock_datasource
Real-Time Stock Quote Subscriber
Yourdaylight/stock_datasource
Streams live A-share, Hong Kong and ETF quotes from a receiver node over a local WebSocket server, with built-in price and volume alert rules.
Tushare Plugin Builder
Yourdaylight/stock_datasource
Turns a Tushare API doc URL into a full data plugin for the stock_datasource repo: extractor, ClickHouse schema, query service, config and curl examples.
MCP API Key Authentication
Yourdaylight/stock_datasource
Sets up and troubleshoots MCP API key authentication for a stock data service, covering key creation, client configuration and per-tool usage statistics.
Stock Data Assistant
Yourdaylight/stock_datasource
Queries A-share, Hong Kong, ETF and index market data over MCP, streams live quotes by WebSocket, and lets you drive both from WeChat through picoclaw.
Related
Works with
Categories
Questions about Stock Market Data MCP Query
What does Stock Market Data MCP Query do?
Queries historical A-share, Hong Kong stock, ETF and index data through an MCP server: daily K-lines, financial statements, market indicators and screening. The skill needs a `STOCK_MCP_TOKEN` environment variable, a JWT bought from the management platform, and optionally `STOCK_MCP_SERVER_URL` for the server address. It first checks that the token is set; if not, it walks you through subscribing on the platform's MCP data query page, buying a quota pack, copying the issued token and exporting it.
When should I use Stock Market Data MCP Query?
Stock Market Data MCP Query fits situations like: pulling daily K-line data for an A-share, Hong Kong stock, ETF or index; fetching balance sheet, income or cash flow statements; screening or batch-querying market indicators through MCP.
How do I install Stock Market Data MCP Query in Claude Code?
Run `npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a claude-code`. Or copy the skill folder (skills/stock-mcp-query in Yourdaylight/stock_datasource) into .claude/skills/stock-mcp-query in your project. Claude Code loads it when a task matches its description.
How do I install Stock Market Data MCP Query in Codex?
Run `npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a codex`. Or copy the skill folder (skills/stock-mcp-query in Yourdaylight/stock_datasource) into .agents/skills/stock-mcp-query in your project. Codex loads it when a task matches its description.
Can I use Stock Market Data MCP Query in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Yourdaylight/stock_datasource --skill stock-mcp-query -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stock-mcp-query, .gemini/skills/stock-mcp-query, .github/skills/stock-mcp-query and .opencode/skills/stock-mcp-query in your project.
What does Stock Market Data MCP Query need to run?
Going by SKILL.md and its folder, Stock Market Data MCP Query needs credentials named STOCK_MCP_TOKEN. Our summary lists: A STOCK_MCP_TOKEN issued by the management platform; Optionally a STOCK_MCP_SERVER_URL for the MCP server; An MCP-capable client such as DeepSeek Harness, Claude Code or Cursor.
Does Stock Market Data MCP Query access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Stock Market Data MCP Query safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Stock Market Data MCP Query use?
Stock Market Data MCP Query is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Stock Market Data MCP Query use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Stock Market Data MCP Query?
Skills that share tags, products or a category with Stock Market Data MCP Query: Alpha Desk Investment Research (JingHao-Leon/dsh-alpha-desk, 181 stars), Senpi Market Pulse (Senpi-ai/senpi-skills, 134 stars), Vibe-Trading Finance Toolkit (HKUDS/Vibe-Trading, 35k stars) and Tradingview MCP (atilaahmettaner/tradingview-mcp, 5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Stock Market Data MCP Query?
Yourdaylight (a GitHub user) maintains it in Yourdaylight/stock_datasource, which has 189 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 8, 2026.
Source: Yourdaylight/stock_datasource on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.