Equibles

An open-source, self-hosted mini Bloomberg Terminal for AI agents. Scrapes, stores, and serves SEC filings, institutional holdings, insider trading, congressional trades, short data, economic indicators, and daily stock prices — and exposes it all via MCP so your AI assistant can query it directly.

Powers equibles.com.

See docs/ for the user guide and technical documentation.

What's Included

Related MCP server: FinClaw

Quick Start

Docker Compose (recommended)

The fastest way to get everything running. Requires Docker.

git clone https://github.com/daniel3303/Equibles.git
cd Equibles
cp .env.example .env
# Edit .env and set SEC_CONTACT_EMAIL (required by SEC EDGAR fair access policy)
docker compose up

This starts:

Data scraping starts automatically. SEC filings, holdings, insider trades, and congressional trades will begin populating within minutes.

Configuration

All settings can be configured via a .env file in the project root (recommended for Docker) or environment variables.

FINRA Short Data (free API key required):

The FINRA scraper (short volume and short interest) requires a free API key. Without it, the scraper skips gracefully and all other scrapers run normally. Fails-to-deliver data comes from SEC and works without FINRA credentials.

To get a key:

1. Go to the FINRA API Console and sign in (a Google account works)

2. Open the API Credentials menu and create a new API Key

3. Copy the Client ID and Client Secret

4. Set Finra__ClientId and Finra__ClientSecret in your .env file or environment variables

The older developer.finra.org "Teams & Apps" flow has been retired — use the API Console above.

FRED Economic Data (free API key required):

The FRED scraper requires a free API key from the Federal Reserve Bank of St. Louis. Without it, the scraper skips gracefully and all other scrapers run normally.

To get a key:

1. Register at fred.stlouisfed.org/docs/api/api_key.html

2. Copy the 32-character API key

3. Set Fred__ApiKey in your .env file or environment variables

Ticker Filtering (optional):

By default, all tickers are synced. To limit data syncing to specific stocks, set a single ticker list that applies to all scrapers:

# .env — sync only these tickers (applies to all scrapers)
Worker__TickersToSync__0=AAPL
Worker__TickersToSync__1=MSFT
Worker__TickersToSync__2=GOOGL

When not set, all stocks are synced.

Minimum Sync Date (optional):

By default, all scrapers start from January 2020. Set a more recent date for faster initial sync, or go as far back as 2000-01-01 for more historical data:

# .env — start syncing from 2024 instead of 2020
Worker__MinSyncDate=2024-01-01

Embedding (opt-in):

Update notifications (optional):

Authentication (optional):

When set, the web portal requires login and the MCP server requires Authorization: Bearer <key> header. When unset, everything is open access (default).

Updating

The web portal checks GitHub Releases on a schedule and shows a banner when a newer version is available (disable with CHECK_FOR_UPDATES=false). To update to the latest release:

Docker Compose:

git pull
docker compose up -d --build

From source:

git pull
dotnet build Equibles.sln

Database migrations are applied automatically on startup. Review the changelog for notable changes before upgrading.

Web Portal

The web portal at http://localhost:8080 provides a browser-based interface for exploring data:

• Stocks — Browse and search all tracked companies, view price charts with technical indicators (SMA, EMA, RSI, MACD, Bollinger Bands), golden/death-cross and price-streak badges, performance versus SPY, plus per-stock tabs for institutional holdings, short data, SEC filings, financial statements, insider trading, proposed (Form 144) sales, fund holdings (NPORT), fund operations (N-CEN), exempt offerings (Form D), and congressional trades

• Institutions — Browse institutional holders (hedge funds, asset managers), view detailed profiles with portfolio breakdowns, industry allocation, quarterly activity, backtesting, and side-by-side comparisons. Filers are scored on risk-adjusted performance (alpha vs. a benchmark) and a Smart Money Index page aggregates the highest-scoring funds into a consensus signal. Includes a holdings screener with filters (filer count, value, float %, location, AUM/position-count, industry) and CSV export

• Advisers — Browse SEC-registered investment advisers (/advisers), ranked by assets under management, with per-firm profiles (regulatory AUM, main office, employee count, fee structure)

• Insider Trading — Dashboard showing the top insider buys, sells, and biggest transactions over the last 90 days

• Short Activity — Most-shorted leaderboard (/most-shorted, ranked by FINRA short interest) and largest daily short volume (/short-volume), each with a date selector, server-side sort, and pagination

• Economy — Browse FRED economic indicators grouped by category (interest rates, inflation, employment, GDP, etc.) with charts and statistics

• Futures — CFTC Commitments of Traders positioning data for 30+ futures contracts (commodities, indices, currencies) with commercial/non-commercial position charts

• Market — CBOE market indicators: VIX volatility index with OHLC charts, put/call ratios (equity, index, total, VIX, ETP)

• Search — Global search across stocks, institutions, insiders, and congress members with category filtering and date ranges

• Status — System health, worker status, data counts, and error log

MCP Server

The MCP server exposes financial data tools for AI assistants (Claude, ChatGPT, etc.):

• Institutional Holdings — Top holders, ownership history, institution portfolios and summary, sector allocation, quarterly activity, most-held stocks, consensus holdings, fund overlap, market-wide 13F activity, institution search

• Insider Trading — Insider transactions, ownership summary, proposed (Form 144) sales, insider search

• Congressional Trading — Trades for a ticker, trades by one member, member search

• SEC Documents — Full-text search, semantic search, document browsing, keyword search within filings

• Financial Statements — XBRL fact time series per ticker, cross-ticker fact comparison, full income statement / balance sheet / cash flow per fiscal period

• Fund & Adviser Filings — Fund portfolio holdings (NPORT), registered-fund operations (N-CEN), exempt offerings (Form D), and SEC-registered investment-adviser lookup and search (Form ADV)

• Short Data — Daily short volume, market-wide largest daily short volume, bi-monthly short interest, and the latest short-interest snapshot across tickers

• Economic Indicators — FRED data lookup, latest macro snapshot, indicator search across categories

• Stock Prices — Daily OHLCV history with adjusted close, latest close across one or more tickers, and on-demand technical indicators (EMA, Stochastic Oscillator, Average True Range, On-Balance Volume, Bollinger Bands)

• Futures Positioning — COT positioning data, latest snapshot across all contracts, contract search

• Market Indicators — VIX historical data, put/call ratios by type (equity, index, total, VIX, ETP)

• Government Contracts — Federal contract awards won by a ticker (awarding agency, amount, period dates) and a ranking of the top public-company contractors by total federal dollars over a date range (USAspending.gov)

• FDA Catalysts — Scheduled FDA advisory-committee (AdComm) meetings over a date range — the regulatory catalyst dates that move biotech and pharma stocks (FDA.gov)

Connecting to Claude Desktop

Add this to your Claude Desktop config file (claude_desktop_config.json):

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "equibles": {
      "url": "http://localhost:8081/mcp"
    }
  }
}

Restart Claude Desktop and the Equibles tools will be available. You can then ask questions like "Who are the top institutional holders of AAPL?" or "Search Apple's latest 10-K for revenue growth discussion."

Connecting to Claude Code

Add the MCP server to Claude Code:

claude mcp add equibles --transport http http://localhost:8081/mcp

Connecting to ChatGPT Desktop

Add this to your ChatGPT Desktop config file:

macOS: ~/Library/Application Support/com.openai.chat/mcp.json Windows: %APPDATA%\com.openai.chat\mcp.json

{
  "servers": {
    "equibles": {
      "url": "http://localhost:8081/mcp"
    }
  }
}

Restart ChatGPT Desktop and the Equibles tools will be available.

Connecting to OpenClaw

In OpenClaw, add an MCP server with the URL http://localhost:8081/mcp (HTTP transport).

Other MCP Clients

Any MCP-compatible client can connect to http://localhost:8081/mcp (HTTP transport).

Vector Embeddings (advanced, opt-in)

Vector embeddings enable semantic search over SEC filings (e.g., "find revenue growth discussion in Apple's 10-K"). This requires downloading the Ollama runtime (~2GB) and the Qwen3-Embedding-0.6B model (~640MB).

docker compose --profile embedding up

This adds:

Without the embedding profile, BM25 full-text search via ParadeDB still works out of the box — vector search is purely additive.

Bundled Ollama is the default because it needs no GPU and runs anywhere. For bulk embedding at scale, point Embedding__Provider=OpenAI at a batched server such as vLLM or Text-Embeddings-Inference — they continuously batch on the GPU and are far faster than Ollama for large corpora. See docs/guide/how-to-use-external-embedding-endpoint.md.

Screenshots

Contributing

See CONTRIBUTING.md for development setup, project architecture, and how to extend the platform. Contributors must sign the Contributor License Agreement — this is handled automatically by a bot when you open a pull request.

License

AGPL-3.0

Author

Daniel Oliveira