{
  "markdown": "# stox-mcp\n\n**Give your AI the numbers that matter.** An MCP server over the\n[stox.market](https://stox.market) metric layer — *context, not data*: every\nfinance feed hands a model raw bars and statements, and the model still can't\nanswer \"is this number good?\". This server ships the judgment layer instead.\n\n**Live endpoint:** `https://mcp.stox.market/mcp` (streamable HTTP) ·\n**Demo & docs:** [stox.market/mcp](https://stox.market/mcp)\n\n```bash\nclaude mcp add --transport http stox https://mcp.stox.market/mcp\n```\n\n## Tools\n\n| tool | what it answers |\n|---|---|\n| `fingerprint` | The character of one stock: 16 percentile scores vs the S&P 500 cohort across four panels (Market Beat, Trend Persistence, Business Growth, Pressure), the P3 composite, curated peers, a one-line read. ~550 tokens. |\n| `compare` | The 16-score matrix for 2–5 tickers, side by side. |\n| `peers` | TRUE competitive peers — curated from segment overlap, not GICS (Costco → WMT/TGT/KR, not \"Discount Stores\"). |\n| `theme_cluster` | Who a stock *moves with*: co-movement clusters from price behavior (market-removed residuals → random-matrix cleaning → Ward linkage). |\n| `screen` | Min/max bounds on any of the 16 metrics — momentum and fallen-leader queries in one call — optionally per sector, sorted by the P3 composite or any single metric. |\n| `market_regime` | Market-stress stance, per-indicator bands, the VIX 5-yr percentile (the one input validated as predicting forward risk), and the S2 stress-confirmation badge. |\n\n## Design\n\n- **Token economy** — compact JSON, score + band + a one-line read; a\n  fingerprint is ~550 tokens where a statements dump is 20,000.\n- **Percentiles, not raw numbers** — every score is a cross-sectional rank\n  against the real cohort (100 = best), so \"is it good?\" is answered by\n  construction.\n- **Provenance** — snapshot dates on scores, links back to the full picture.\n- **Informational only** — descriptive statistics; never investment advice,\n  no buy/sell recommendations. Derived metrics only; this is not a\n  market-data feed.\n\n## The human-readable twin\n\nThe same metric layer renders as editorial leaderboards at\n[stox.market/lists](https://stox.market/lists) — 31 boards plus sector\nslices and frozen earnings-season editions, refreshed on automated weekly\nlanes. A board is where a name catches your eye; `fingerprint` is how your\nagent vets it in one call.\n\nUniverse: S&P 500 + NASDAQ-100 + curated ETFs. Coverage and metric\ndefinitions: [stox.market](https://stox.market).\n",
  "bytes": 2507,
  "sha": "744d1e3c9f03f6d5e0672dabc03191ff725360f8a1d7a7513f05c6783d6fc844",
  "repo_slug": "nirajagarwal/stox-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_nirajagarwal_stox_mcp_4a9e989b/readme"
}