@romaco/mcp

MCP server for romaco-charts. Control your trading chart from Claude, Cursor, or any MCP-compatible AI agent.

npx @romaco/mcp

Philosophy

Romaco MCP is compression-first. Tools return features and decisions, not raw OHLCV. Every tool's typical output is under 2 KB. Raw payloads (full chart state, snapshots, all-bar indicator series) exist but are gated behind acknowledgeHighTokenCost: true — the agent must consciously opt in and the user must explicitly request raw data.

The rule: the agent never computes, it always queries. An agent reasoning over features cannot hallucinate prices; an agent given a 70 KB raw OHLCV dump will burn its context window before it can finish a thought.

Cost table

Related MCP server: tradingview-mcp

30-second start

# 1. Install
npm install -g @romaco/mcp

# 2. Wire it into Claude Code (run from your project root)
cat > .mcp.json <<'EOF'
{ "mcpServers": { "romaco": { "command": "romaco-mcp" } } }
EOF

Then start Claude Code and prompt:

Use romaco_setup_chart to analyze AAPL daily with the trend_analysis preset.

That's it. The MCP server fetches yfinance data (with disk cache + cookie/crumb handshake), runs full technical analysis, and returns a compressed MarketSummary (~500 tokens) to Claude. No 429s, no manual auth.

Live chart control (optional)

To let Claude drive a real chart — drawings, indicators, alerts visible in your browser — mount <McpBridge /> next to your TradingTerminal:

import { TradingTerminal, McpBridge, type TradingTerminalRef } from 'romaco-charts/react';
import { useRef } from 'react';

function App() {
  const ref = useRef<TradingTerminalRef | null>(null);
  return (
    <>
      <TradingTerminal ref={ref} data={candles} symbol="AAPL" />
      <McpBridge chartRef={ref} />
    </>
  );
}

See examples/pro-volatility-scanner for a complete setup. With <McpBridge /> mounted, the chart-bridge tools (add_indicator, add_drawing, add_alert, capture_snapshot, …) become available.

Data cache

Every successful yfinance fetch is cached to ~/.romaco/cache/ with per-timeframe TTL (1m→1min, 1h→1h, 1d→24h, …). A grid of N widgets requesting the same symbol triggers one upstream fetch. Wipe the cache anytime with rm -rf ~/.romaco/cache, or override the location with ROMACO_CACHE_DIR=/tmp/cache.

What it does

Exposes 20+ MCP tools in two categories:

Headless tools — work without a browser, load data and run analysis server-side:

• romaco_setup_chart — one-command setup: load + preset + analyze (recommended first call)

• romaco_load_candles — fetch OHLCV from Yahoo Finance (free) or pass your own array

• romaco_analyze_market — full technical analysis: trend, S/R levels, RSI/MACD/divergences, volatility, patterns

• romaco_thesis — computed bull/bear debate → verdict (long/short/stand_aside) + confidence + entry/stop/target setup; stands aside when R/R is poor (won't fake a signal)

• romaco_find_levels — support/resistance via K-means + Volume Profile (POC/VAH/VAL)

• romaco_detect_patterns — H&S, double top/bottom, triangles, flags

• romaco_calculate_position_size — pure-math risk-based position sizing with R/R + breakeven win-rate

• romaco_list_templates — catalog of drawing templates (trendline, fib, channels, …)

Chart-bridge tools — control a live Romaco chart in the browser:

• romaco_add_indicator — EMA, RSI, MACD, Bollinger, ATR, 29+ indicators

• romaco_add_drawing — trendlines, Fibonacci, horizontal lines, channels, rectangles

• romaco_add_alert — price alerts with direction (above/below/cross)

• romaco_capture_snapshot — PNG/JPEG base64 for vision LLMs

• romaco_open_paper_position — simulated long/short with SL/TP

• romaco_get_chart_context — complete chart state as JSON

• romaco_get_visible_candles — OHLCV in current viewport

• romaco_set_zoom / romaco_reset_view — zoom control

• romaco_clear_drawings — remove all drawings

• romaco_list_panes — enumerate main + subpanel panes (e.g. RSI subpanel id)

• romaco_get_indicator_values — read computed indicator series (by id or name)

• romaco_go_to_timestamp — scrub viewport to a given timestamp

Install

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "romaco": {
      "command": "npx",
      "args": ["-y", "@romaco/mcp"]
    }
  }
}

Restart Claude Desktop.

Claude Code

claude mcp add romaco -- npx -y @romaco/mcp

Or add to your project's .mcp.json:

{
  "mcpServers": {
    "romaco": {
      "command": "npx",
      "args": ["-y", "@romaco/mcp"]
    }
  }
}

Cursor / other MCP clients

Any client that supports stdio MCP servers works. Point it at npx @romaco/mcp.

Usage

Headless analysis (no browser needed)

Load 500 candles of AAPL 1h from yfinance, then analyze the market.

Claude will call:

1. romaco_load_candles → fetches from Yahoo Finance

2. romaco_analyze_market → returns compressed MarketSummary (~500 tokens)

3. romaco_find_levels → S/R zones, POC, VAH, VAL

4. Reasons over the features → tells you what it sees

Live chart control (with browser)

Add <McpBridge /> to your chart app:

import { TradingTerminal, McpBridge } from 'romaco-charts/react';

function App() {
  const ref = useRef(null);
  return (
    <>
      <TradingTerminal ref={ref} symbol="AAPL" timeframe="1h" datafeed={myDatafeed} />
      <McpBridge chartRef={ref} />
    </>
  );
}

Then from Claude:

Add EMA 20 and RSI 14 to the chart, draw a Fibonacci from the last swing low to swing high,
and capture a snapshot so I can see it.

Data sources

Bring your own key (BYOK) — Coming in v1.1: Alpaca, Polygon.io, FMP.

Configuration

# Custom port
npx @romaco/mcp --port 3200

# Or via env
ROMACO_MCP_PORT=3200 npx @romaco/mcp

Set the same port in <McpBridge port={3200} />.

Free vs Pro (ROA-I)

This MCP is the free hook. It runs fully standalone — analysis is computed locally and limited by whatever model your agent uses.

With a ROMACO_TOKEN set, analysis tools (starting with romaco_analyze_market) forward the heavy compute to ROA-I at ROMACO_API_URL. No token, or backend unreachable → it falls back to local compute, so the free path never breaks.

Get a key at romaco.io. See .env.example.

Example prompts

Institutional analysis:

"Load TSLA 4h from yfinance, analyze the market, find key levels, detect any chart patterns, then draw the Fibonacci retracement of the last swing on the chart and add an alert at the 0.618 level."

Conditional automation:

"Load AAPL 15m, run full analysis. If RSI shows bullish divergence and price is near a support level, open a paper long 100 shares with stop loss at the VAL of the Volume Profile."

Pattern scanner:

"Load SPY 1d and detect patterns. For any head & shoulders found, tell me the target price and invalidation level."

Requirements

• Node.js >= 18

• For chart-bridge tools: romaco-charts >= 1.0.0-beta.6 with <McpBridge /> in your app

Links

• romaco-charts npm

• Documentation

• GitHub