{
  "markdown": "# Fahali — Financial Risk MCP Server for AI Agents\n\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-com.fahaliai%2Ffahali-C9A961)](https://registry.modelcontextprotocol.io/v0/servers?search=fahali)\n[![Methodology](https://img.shields.io/badge/judged%20publicly-misses%20included-0B0A09)](https://fahaliai.com/methodology)\n\n**Give your agent a risk conscience.** Fahali gives AI agents a callable financial-risk layer: portfolio risk, stress losses, crypto risk, contagion, crash precursors and market verdicts. Read-only — your agent already fetches prices; Fahali tells it what those prices mean for capital at risk. It returns a judged read with its confidence, the inputs it is missing, and a signed receipt, so your agent can check its own conviction against something scored against outcomes instead of raw prices it has to interpret blindly.\n\n> **Observation, not advice.** Fahali watches and explains market risk. It never tells you or your agent what to buy or sell. Read-only: no order routing, no path to capital.\n\n## Why an agent cites Fahali instead of a price feed\n\n- **Verified lead time.** Per engine, the median hours ahead of the move on its correct material warnings, scored against what happened, with the misses in the same record. Your agent can weight a signal by proven lead, not by tone. Public, no key: `GET /api/track-record/lead-time`.\n- **Signed receipts.** Every verdict carries a SHA-256 receipt and a provenance root. When your agent quotes Fahali, it can attach proof of what was said and when.\n- **A judged record with public replays.** Predictive signals are graded against a disclosed, versioned method at their own horizon, and wrong calls stay on the record. Analytical engines are labelled observation-only rather than scored as forecasts, because grading an observation against a price move would manufacture a hit rate that means nothing. Methodology: [fahaliai.com/methodology](https://fahaliai.com/methodology).\n- **Honest absence.** Missing data says so. Quiet markets resolve as unresolved, never as wins. Some tools abstain by design: whale tracking returns an explicit \"no on-chain data source\" rather than inventing positions.\n\nCoverage is crypto 24/7 and US equities and ETFs during market hours. Live coverage and engine counts are reported at `GET /api/public/stats` rather than asserted here, because the active set changes.\n\n## See it before you sign up\n\nThe lead-time record is public. This is the fastest way to confirm Fahali is scored against outcomes:\n\n```bash\ncurl https://app.fahaliai.com/api/track-record/lead-time\n```\n\n## Connect\n\n**Remote MCP (recommended, nothing to install):**\n\n```\nStreamable HTTP:  https://mcp.fahaliai.com/mcp\nSSE (legacy):     https://mcp.fahaliai.com/sse\n```\n\nAuth: OAuth 2.1 (\"Connect with Fahali\") or a static key, `Authorization: Bearer sk_live_...`. Grab a free developer key (50 calls/day, no card) at [app.fahaliai.com/developer](https://app.fahaliai.com/developer). In Claude, ChatGPT, or Cursor, add the URL above as a connector. Listed in the official MCP registry as `com.fahaliai/fahali`.\n\n**Run this repo as a local stdio proxy:**\n\n```bash\nnpm install\nnpm run build\nFAHALI_API_KEY=sk_live_... node dist/index.js --stdio\n```\n\nIt forwards each tool call to the upstream Fahali API; tier is enforced upstream.\n\n## Example: a pre-trade risk check\n\n[`examples/pre-trade-check`](examples/pre-trade-check) is a runnable agent (zero dependencies, one command) that asks Fahali, before a position is opened: is a flash-crash precursor firing, what is the judged read and what data is missing, and how early does the record say this engine usually warns. It then prints a `PROCEED` / `CAUTION` / `HOLD` posture and the receipt.\n\n## Tools\n\nAround 30 tools. Most are read-only market intelligence; a few agent-workspace tools (memory, custom alerts) write only to your own workspace, never to markets. Highlights:\n\n| Tool | Returns |\n|------|---------|\n| `fahali_get_market_verdict` | Per-symbol verdict: direction, confidence, reasoning, expected move, horizon |\n| `fahali_get_lead_time` | The verified, outcome-scored lead-time record (public) |\n| `fahali_get_forecast` | Probabilistic forecast over the signal's own registered horizon (6-72h), with an uncertainty cone, Brier-scored |\n| `fahali_get_flash_crash_risk` | Flash-crash precursor strength, or an explicit abstention |\n| `fahali_get_track_record_scorecard` | The judged record with per-horizon base rates and lift |\n| `fahali_get_contagion_map` | Cross-asset tail-dependence and correlated clusters |\n| `fahali_get_microstructure_proxy` | Absorption inferred from public microstructure only - we do not see off-exchange prints |\n| `fahali_get_capital_flow` | Order-flow imbalance proxy (no fabricated institutional/retail split) |\n| `fahali_get_market_regime` | Current regime read |\n| `fahali_run_shock_test` | Stress-test a portfolio against a scenario |\n\nFull tool schemas: [mcp.fahaliai.com](https://mcp.fahaliai.com/).\n\n## Pricing\n\nFree developer key (50 calls/day) for exploration. Agent lanes from $49/mo (10k calls), $199 (100k), $999 (1M). Human app tiers from $19/mo at [fahaliai.com](https://fahaliai.com).\n\n## Links\n\n- App: [app.fahaliai.com](https://app.fahaliai.com)\n- MCP docs / health: [mcp.fahaliai.com](https://mcp.fahaliai.com/)\n- Methodology (how signals are graded): [fahaliai.com/methodology](https://fahaliai.com/methodology)\n- Developer / API: [fahaliai.com/developer](https://fahaliai.com/developer)\n- Privacy: [app.fahaliai.com/privacy](https://app.fahaliai.com/privacy)\n\nBuilt by [Future Legends Inc](https://fahaliai.com). Observation, not advice.\n",
  "bytes": 5638,
  "sha": "f689dc46ff01c9bc802fabb5b94eba8737273fd33e7aedce18c72df20187502f",
  "repo_slug": "future-legends-inc/fahali-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_fahaliai_fahali_46fe3107/readme"
}