Haruspex
About
Get stock score (e.g. /score NVDA)
Details
- Author
- haruspex-guru
- Categories
- Finance, Other
Jump to
Setup
Install Haruspex in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/haruspex-guru/haruspex-skills
Follow the installation instructions in the repository README, then restart your MCP client.
- An MCP server—@haruspex-guru/mcp-server, aModel Context Protocolserver that exposes the Haruspex stock-analysis API as tools (get_stock_score,get_stock_score_history,get_batch_scores,search_stocks,get_stock_news). Its source andDockerfilelive inmcp-server/, and it is published to npm as@haruspex-guru/mcp-server.
- A set ofAnthropic Agent Skills(inskills/) that build structured trading workflows — single-ticker reads, watchlist scans, thesis checks, a Japanese-language variant — on top of that MCP server.
The MCP server lives inmcp-server/and is published as@haruspex-guru/mcp-server. It speaks the Model Context Protocol over stdio and exposes five tools:
docker build -t haruspex-mcp mcp-server/ # or build from repo root: docker build -t haruspex-mcp .
The server readsHARUSPEX_API_KEYat runtime for live data; get a key athttps://haruspex.guru/settings. The Anthropic Skills below depend on this MCP server for their data — without it installed, the skills detect that, output install instructions, and stop; they will never fabricate analysis.
Each skill is a folder containing aSKILL.mdwith YAML frontmatter, areference.mdfor deeper docs, and anexamples.mdwith full example dialogues usingreal captured data.
- Install skills.From this repo:
git clone https://github.com/Haruspex-guru/haruspex-skills.git mkdir -p ~/.claude/skills cp -r haruspex-skills/skills/ ~/.claude/skills/
claude mcp add-json --scope user haruspex '{ "command": "npx", "args": ["-y", "@haruspex-guru/mcp-server"], "env": { "HARUSPEX_API_KEY": "hrspx_demo_public_REPLACE_ME" } }'
claude mcp list # haruspex should show ✓ Connected
/mcp # browse Haruspex tools /skills # see all 4 haruspex skills (✔ on)
- Enable code executionin Claude.ai if you haven't already (Settings → Capabilities).
- Package each skill as a ZIP.From this repo:
cd skills for d in /; do (cd "$d" && zip -r "../${d%/}.zip" .); done
Heads-up: skills uploaded to claude.ai are subject to Anthropic's review guidelines for third-party content. "Only install skills from trusted sources" applies — Haruspex skills do not execute arbitrary code, but users should still review the SKILL.md files before installing.
The Claude API supports Agent Skills programmatically. Bundle the skill directories with your request and pass the MCP server configuration alongside. See Anthropic's official Skills API docs for current syntax.
The native Claude Desktop app doesnotload user-installable filesystem skills as of v0.1.0 of this repo (April 2026). Desktop's skills runtime currently only surfaces a built-in set (docx, pdf, pptx, etc.).
The MCP server side does work in Claude Desktop — seeshared/MCP_SETUP.mdforclaude_desktop_config.jsonsetup. But without a skills runtime, you'd be left calling MCP tools freeform rather than getting the structured workflow these skills enforce.
For Desktop users today: install Claude Code and use it from your terminal, or use claude.ai web with the ZIP upload flow above. Anthropic may add filesystem-skills support to Desktop later; this repo will update when that ships.
- A Haruspex API key — sign up athttps://haruspex.guru.Never commit your API key to a repository.
- One of: Claude Code, Claude.ai web, or the Claude API.
- Node.js 18+ if you're running@haruspex-guru/mcp-servervianpx.
Full per-surface MCP setup details live inshared/MCP_SETUP.md.
These skills produceanalysis, not advice. Every skill is hard-coded with compliance rules that prohibit direct buy/sell/hold recommendations, price predictions, position sizing, and stop-loss/take-profit specifics. Every skill output includes the canonical disclaimer footer.
The full disclaimer language and the rationale behind each compliance rule are inshared/DISCLAIMER.md. Treat that file and the "Compliance rules (NEVER VIOLATE)" sections of eachSKILL.mdas load-bearing.
Nothing in this repository is investment advice. Haruspex scores are quantitative signals derived from public data, provided for informational purposes only.
The Haruspex score is a composite of topic dimensions (e.g.competitors,earnings,supplychain,us_china_official). Plain-English descriptions of all 16 are inshared/DIMENSIONS.md. The scoring methodology itself is proprietary and intentionally not documented here.
SeeCONTRIBUTING.md. The short version:
- Open an issue before opening a PR for non-trivial changes.
- Runbash scripts/validate-skills.shbefore submitting.
- Examples must usereal captured datafrom the live API. Fabrication will be rejected.
- Compliance language is non-negotiable.
eval/queries/contains ~20 trigger-test queries per skill (half should-trigger, half should-not, with cross-skill ambiguity cases). Use them when revising any skill'sdescriptionfield. Seeeval/README.mdfor the manual evaluation procedure.
MIT. The MCP server and skills (instructions and examples in this repository) are MIT-licensed. The Haruspex scoring algorithm and underlying data are proprietary; access is governed by theHaruspex API Terms of Service. SeeNOTICEfor the full scope statement.
Built for the Haruspex community, inspired by patterns we've seen work in real trader workflows. Submissions to the officialanthropics/skillscatalog will follow once the skills have a stable shape here.
Access ROIC.AI financial data from AI tools, including company financials, ratios, prices, transcripts, and market research data.
Hosted MCP server for AI-enriched financial news — full-text and ticker-scoped news search, trending stories, and SEC Form 4 insider activity, each story scored 1–10 for relevance (OAuth 2.1, free tier 100 calls/hour).
Read-only MCP for U.S. household financial distress data: 96 indicators, the American Distress Index (ADI), and county-level distress scores for all 3,144 U.S. counties.
Read-only MCP for U.S. household financial distress data: 96 indicators, the American Distress Index (ADI), and county-level distress scores for all 3,144 U.S. counties.
Hosted MCP server for Chinese A-share and ETF market data, including prices, fundamentals, capital flows, financial statements, real-time quotes, and news.
Clean SEC EDGAR company financials, ratios, filings, and 10-K/10-Q sections as normalized JSON — a hosted MCP server with 5 tools and a free tier.
US stock market & financial data — SEC filings full-text search, XBRL fundamentals, 13F institutional holdings, insider & congressional trades, earnings-call transcripts, short interest, and FRED macro; 90+ tools, free tier, self-hostable.
Market intelligence your AI agent can call
Investment analysis for 2,260+ US equities — 43 tools for stock screening, ML earnings predictions, insider/congressional trades, macro signals, Fear & Greed, and alternative data.
SEC filings, earnings transcripts, guidance signals & macro calendar for S&P 500. 11 MCP tools for algo traders and financial analysts using Claude Code.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
