Financial-API
同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service providing real-time and historical stock market data, financial statements, indices, sectors and limit-up data for AI agents, quantitative research and application development.
Runs with mockssource: GitHubhomepageTypeScriptMITcommit 3bca7805a412
TypeScript, MIT licensed. The project labels itself: a share, ai agent, china stock market, cli, duckdb, financial data, mcp and npm package.
Financial-API runs, with stand-ins for the services it depends on. An Argusic agent installed it in 11 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
Python marketdb package installed in venv with all dependencies, 274/275 Python tests pass (1 intentional skip), CLI builds and runs (version, doctor, capabilities, mock-verified remote commands), marketdb CLI commands work, skill contract docs are synchronized, and code formatting is clean. Node 18 prevents vitest test runner execution. A real API Key from fuyao.aicubes.cn is required for live remote verification.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 87 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- CLI uses import.meta.dirname (Node 21+); crashes on Node 182 minutes
- Bundled vitest 4.x fails on Node 18 (requires ^20.0.0 || ^22.0.0)1 minute
- Direct pip install blocked by PEP 668 externally-managed environment1 minute
- pytest not installed in venv (opt-dependencies dev omitted)1 minute
- Install time
- 11 minutes
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 4 hit, 3 fixed with no human help
- How the result was proved
- cd /work/repo/python && python -m pytest tests/ --tb=line -q -> 274 passed, 1 skipped; cd hithink-finance-cli && node dist/cli/main.js version --format json -> exit 0, version 0.1.13; node dist/cli/main.js doctor --format json -> duckdb available; mock server: market calendar -> ok=true count=3, symbol search -> ok=true count=1, market snapshot -> ok=true price=1800.5; Python client via mock: tickers_search ok count=1 name=贵州茅台; marketdb version -> marketdb 0.1.0 schema 1.0.0; prettier --check -> all clean; sync_skill_contracts.py --check -> synchronized
- Model tokens used
- 116,389
- Exact commit tested
- 3bca7805a412
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec /bin/sh -lc 'echo "Start: 07:16, End: $(date +%H:%M)"' in /work/repo succeeded in 0ms: Start: 07:16, End: 07:27 exec /bin/sh -lc "cat << 'EOF' EOF' in /work/repo succeeded in 0ms: The result has been produced comprehensively. All components are installed and verified. The single… tokens used 116,389 The result has been produced comprehensively. All components are installed and verified. The single…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 11 minutes.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Hit 4 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 87.00 | 0.10 |
Topics (from GitHub)
a-shareai-agentchina-stock-marketcliduckdbfinancial-datamcpnpm-packagequantitative-financerest-api
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/financial-api)Questions
- Does Financial-API run?
- Financial-API runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 11 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test Financial-API?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3bca7805a412. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Financial-API?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Financial-API take to install?
- 11 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does Financial-API need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Financial-API?
- 4 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for Financial-API?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.