★ ★ ★LIVE97 COINS ANALYZED BY CLAUDE MCP·VIEW SKILLS →★ ★ ★
MCP
claude.analyze("BTCUSDT")→ [buy] signal detectedmcp.draw_levels(resistance=98000)→ [drawn] on chartclaude.scan_watchlist(coins=100)→ [42] buy signals foundmcp.connect("tradingview")→ [connected] daily TFclaude.detect_sr("SOLUSDT")→ [S: $165] [R: $185]claude.analyze("ETHUSDT")→ [neutral] consolidatingmcp.screenshot_chart("BNBUSDT")→ [captured] analyzing...claude.score_quality("XRPUSDT")→ score: 78/100mcp.set_timeframe("1D")→ [ok] chart updatedclaude.analyze("BTCUSDT")→ [buy] signal detectedmcp.draw_levels(resistance=98000)→ [drawn] on chartclaude.scan_watchlist(coins=100)→ [42] buy signals foundmcp.connect("tradingview")→ [connected] daily TFclaude.detect_sr("SOLUSDT")→ [S: $165] [R: $185]claude.analyze("ETHUSDT")→ [neutral] consolidatingmcp.screenshot_chart("BNBUSDT")→ [captured] analyzing...claude.score_quality("XRPUSDT")→ score: 78/100mcp.set_timeframe("1D")→ [ok] chart updated
BACK TO CLAUDE SKILLS
◈

mcp_screenshot_chart

MCP IntegrationMCPVision
INSTALLATION
$python -c "exec(open('mcp_screenshot_chart.py').read())"
#or paste directly into your Claude Code terminal
[ ABOUT ]

Captures a PNG screenshot of the active TradingView chart window via MCP and returns the image as a base64-encoded string. The encoded image is structured in the Anthropic API's `image` content block format so it can be passed directly to `claude.messages.create` for vision-based analysis without any intermediate file I/O.

Most effective when used together with `mcp_add_indicator` — first render the chart in a known state (e.g. EMA + RSI), then screenshot and pass to Claude for pattern recognition tasks that benefit from visual context rather than raw numerical data, such as trend line detection or chart pattern classification.

[ USAGE EXAMPLE ]
example.py
img = screenshot_chart(client)
# img = {"type": "image", "data": "iVBORw0KGgo..."}
result = analyze_chart_image(img["data"])
[ FULL CODE ]
mcp_screenshot_chart.py
import base64 def screenshot_chart(client): raw = client.call("screenshot", {"format": "png"}) img_b64 = base64.b64encode(raw).decode() return {"type": "image", "data": img_b64}
[ METADATA ]
CategoryMCP Integration
ComplexityIntermediate
LanguagePython 3.10+
TagsMCP, Vision
[ ASK CLAUDE ]

Ask AI about this skill before installing it.

[ RELATED SKILLS ]