mcpField
S
SIWAI

SIWAI

Remote
siwai.appFinance0Updated 2d ago
RepositoryVisit website

About SIWAI

SIWAI is a remote market-analysis service for AI agents, offering read access to chart-pattern scans and market data. It also covers 13F fund tracking and economic, earnings, and dividend calendars.

Key features

  1. 01Daily chart-pattern scans
  2. 02Stock screening and fundamentals
  3. 0313F fund activity tracking
  4. 04News and market calendars
  5. 05Pattern-combination hit rates

Use cases

  1. 01Find today's stock breakout setups
  2. 02Screen stocks by ROE, P/E, and pattern
  3. 03Review funds' quarterly buys and sells
  4. 04Check this week's high-impact economic events

MCP support

SIWAI provides a remote MCP server that exposes market scans, screening, fund tracking, news, and calendars to AI clients over Streamable HTTP. It supports OAuth or API keys; one tool can replace the user's watchlist.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://siwai.app/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://siwai.app/api/mcpAuth required

Tools

Details

From the project README

SIWAI logo

SIWAI MCP server

Remote MCP server for SIWAI, a chart-pattern detection and technical analysis platform. It gives AI agents read access to SIWAI's daily pattern scan, screener, 13F fund tracker, ticker fundamentals, news and economic / earnings / dividend calendars, across stocks, crypto, indices, commodities and forex.

This repository holds the public listing metadata (server.json), docs and logo. The server itself is hosted by SIWAI; there is nothing to install or run locally.

Not financial advice. For informational purposes only. SIWAI finds setups; it does not place trades. The user still sizes the position, places the stop and takes the trade.

What you can ask

  • "Which breakout setups did SIWAI find on stocks today?"
  • "Screen for stocks with ROE above 15%, P/E under 25 and a Breakout pattern."
  • "What did the biggest tracked 13F funds buy or sell in NVDA last quarter?"
  • "What high-impact economic events are on the calendar this week?"
  • "Show me SIWAI's hit rate for Breakout + Impulse setups."

Tools

24 tools; 23 are read-only and one (update_watchlist) replaces the user's watchlist. See docs/tools.md for the full list with annotations and scopes.

Access

The API and MCP server are included with a paid SIWAI subscription. See docs/api-key.md for OAuth, API keys, scopes and daily limits.

Client setup

Claude (claude.ai / Desktop), ChatGPT and other OAuth clients: add a custom connector with URL https://siwai.app/api/mcp and sign in when asked.

Add to Cursor

Cursor with an API key instead of OAuth (.cursor/mcp.json):

{
  "mcpServers": {
    "siwai": {
      "url": "https://siwai.app/api/mcp",
      "headers": { "Authorization": "Bearer siwai_YOUR_KEY" }
    }
  }
}

Clients without remote-server support (via mcp-remote):

{
  "mcpServers": {
    "siwai": {
      "command": "npx",
      "args": ["mcp-remote", "https://siwai.app/api/mcp", "--header", "Authorization: Bearer siwai_YOUR_KEY"]
    }
  }
}

Privacy and support

License

The contents of this repository (metadata and docs) are MIT licensed. The SIWAI service is proprietary and subject to its terms.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.