Skip to content
@ai-intellicore

ai-intellicore

AI IntelliCore Limited

Institutional-grade quantitative risk analytics, built AI-native.

We design and operate proprietary signal systems that turn noisy market, macro, and media data into structured, calibrated intelligence — exposed through web dashboards, a Signals API, and a public MCP server any AI assistant can reason over directly.

What we build

Product Audience Home
FinTurb — systemic-risk dashboards, regime monitors, liquidity intelligence Family offices, CIOs, quant desks, active investors, risk managers, day traders, hedge funds finturb.com
FinTurb Analytics MCP — 26 tools + 3 resources for Claude, ChatGPT, Cursor, and any MCP-compliant client Anyone with an AI assistant finturb.com/mcp-access · repo ↓
FinTurb Signals API — authenticated REST endpoints for the same signal stack Institutional integrations api.finturb.com

The eight pillars

Every product above reads from the same nightly signal pipeline (00:05–04:05 UTC) organised into eight analytic pillars:

  1. Composite risk monitor — 0–100 regime score with AR / turbulence / GDELT decomposition, extended by a 4-way liquidity gate.
  2. Financial turbulence — cross-asset covariance regime with Markov transition probabilities.
  3. Systemic fragility — three-tier Absorption Ratio alerts plus per-asset PC1 / PC2 eigenvector history.
  4. Media sentiment — GDELT-derived tone, volume, and outliers across 27+ assets plus a global geopolitical tension gauge.
  5. Global liquidity — GLI composite with policy / private-sector / cross-border sub-indices and regional breakdown.
  6. Statistical arbitrage — 550+ security scanner for oversold and overbought mean-reversion candidates.
  7. AI-generated intelligence — cross-pillar briefings and narrative commentary, clearly flagged as synthesized vs deterministic.
  8. Supporting analytics — multi-year asset-class returns and a RAG stablecoin scorecard.

Output contract

Every MCP response — and every API payload — carries:

  • summary · one-line human-readable headline
  • generation_mode · deterministic or synthesized provenance flag
  • file_modified · ISO timestamp of the underlying data file

So consumers can reason from a dense headline, drill into structured fields for precision, and verify freshness at the point of use. No silent hallucination layers, no stale caches.

Get started

With Claude, ChatGPT, or any MCP client — paste https://mcp-mkic.pythonanywhere.com/mcp into your connector settings. 50 free queries per 48 h. Full setup guides live in finturb-mcp/docs.

For institutional integrationsapi.finturb.com or reach out at tk.intellicore.ai@gmail.com.

Contact


The Model Context Protocol is a trademark of Anthropic PBC. Past performance is not indicative of future results. All information provided is for research and informational purposes only and does not constitute investment advice.

Pinned Loading

  1. finturb-mcp finturb-mcp Public

    Public documentation and metadata for the FinTurb Analytics MCP server — 26 tools for institutional-grade financial risk analytics (risk regimes, systemic fragility, media sentiment, global liquidi…

    1

Repositories

Showing 2 of 2 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…