Real-time news with bias scoring, live market data, and AI-powered options pricing — all accessible through the Model Context Protocol.

Helium MCP gives your AI assistant access to:

• 3.2M+ news articles from 5,000+ sources, each scored across 15+ bias dimensions
• Balanced news synthesis — left, right, and center perspectives aggregated into one coherent story
• Live market data — price, IV rank, AI-generated bull/bear cases, and price forecasts
• AI options pricing — proprietary ML models for fair-value estimates and probability ITM
• Meme search — semantic search across viral memes with OCR text and captions

50 free queries included. No sign-up required.

Add to your Cursor MCP settings:

{
  "mcpServers": {
    "helium": {
      "url": "https://heliumtrades.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "helium": {
      "type": "streamable-http",
      "url": "https://heliumtrades.com/mcp"
    }
  }
}

Add to your Windsurf MCP settings:

{
  "mcpServers": {
    "helium": {
      "serverUrl": "https://heliumtrades.com/mcp"
    }
  }
}

Add to your .github/copilot-instructions.md or MCP config:

{
  "mcpServers": {
    "helium": {
      "type": "streamable-http",
      "url": "https://heliumtrades.com/mcp"
    }
  }
}

Connect to the streamable HTTP endpoint:

https://heliumtrades.com/mcp

"What's the bull and bear case for Bitcoin?"

get_ticker("BTC")
→ Bitcoin: $71,040.01
  Bull case: "Institutional spot demand resumes... squeeze toward mid/upper-80ks to low-100ks"
  Bear case: "Higher-for-longer rates, persistent ETF outflows... slide into 40–55k plausible"
  Forecast: +1.8% over 37 days (range: -1.2% to +5.0%)
  IV Rank: available
  Options strategies: long vol + short vol packs included

"How biased is CNN?"

get_source_bias("CNN")
→ Emotionality: 7/10
  30+ bias dimensions scored (political lean, fearfulness, opinion, oversimplification...)
  Signature phrases: "trump threatens", "mortgage rates", "nuclear weapons"
  Similar sources: NBC, PBS, AP, Newsweek, CBS
  Per-article bias breakdown on recent stories included

"What are the best options trades right now?"

get_top_trading_strategies()
→ AI-ranked short vol + long vol setups
  Each includes: ticker, price, bull/bear case, 5 probability-weighted outcomes,
  full option pack (strike, expiry, Greeks, ML fair value, probability ITM)

"Give me NVIDIA's full analysis"

get_ticker("NVDA")
→ NVIDIA: $183.91
  5 probability-weighted scenarios (38% mean-revert, 25% +10-25%, 20% -5-12%...)
  Forecast: +4.2% over 37 days (range: -2.6% to +8.9%)
  IV rank, volatility surface, term structure, return profile charts
  27 time-horizon uncertainty visualizations (1-day to 995-day)

"Find me stock market crash memes"

search_memes("stock market crash")
→ Babylon Bee: "Kamala Desperately Googles 'What Is A Stock Market Crash'" (32K likes)
→ "Everyone: 'omg the stock market is crashing!' / 500 cigarettes adapter" (437K likes)
  Full OCR text, source, date, image URLs included

Full-text search across 3.2M+ articles from 5,000+ sources. Filter by source, category, date, and minimum shares. Returns bias scores, AI summaries, and context.

Parameters:

AI-synthesized articles that aggregate multiple sources into balanced coverage. Each story includes a summary, takeaway, evidence breakdown, potential outcomes, and relevant tickers.

Parameters:

Deep bias analysis for any news outlet: political lean, emotional tone, prescriptiveness, signature phrases, similar sources, and historical trends.

Parameters:

Analyze any article URL for per-dimension bias scores: political lean, emotionality, manipulation level, factfulness, and more.

Parameters:

Comprehensive data for any stock, ETF, or crypto: live price, AI-generated bull/bear cases, price forecast, IV rank, volatility surface, and top-ranked options strategies.

Parameters:

Helium's proprietary ML model-predicted fair-value price for a specific option contract. Returns predicted price, probability ITM, and the data date.

Parameters:

Helium's highest-conviction options setups ranked by AI edge score, expected value, and market conditions. Returns both short volatility and long volatility strategies.

Parameters:

Bias scores for every tracked news source — compare outlets, rank by credibility, or build a full media landscape overview. Returns all sources with >100 articles analyzed, sorted by average social shares.

Parameters: None required.

Semantic search across viral memes — images, captions, OCR text, like counts, and source attribution.

Parameters:

Get an API key at heliumtrades.com/mcp-page.

• Helium News Bias Explorer — interactive single-page demo (zero dependencies) that fetches the live source-bias corpus and lets you rank, scatter, or inspect any of the 216 sources across all 37 bias dimensions. The fastest way to feel what the API can do without writing code.
• Helium Ticker Forecast Dashboard — companion dashboard that renders the top 10 short-vol and long-vol candidates with ML 37-day forecasts, uncertainty cones, and bull/bear narratives. Single GET to mcp_top_strategies/.
• Forecaster Honesty Board — post-hoc Brier grades for published prob_itm forecasts.
• helium-mcp-cookbook — eight runnable Python recipes, calibration scorecard, and a citeable bias-corpus dataset snapshot.

Machine-readable index for LLM crawlers: docs/llms.txt and docs/llms-full.txt. Deploy copies at https://heliumtrades.com/llms.txt. Schema.org snippet for mcp-page: docs/mcp-page-schema-snippet.html.

• Helium MCP Page
• Helium News Bias Explorer — live interactive demo (news side)
• Helium Ticker Forecast Dashboard — live interactive demo (markets side)
• helium-mcp-cookbook — seven runnable Python recipes
• Glama
• Smithery
• npm
• Helium Trades
• Privacy Policy

MIT