MCP server · Streamable HTTP · free in beta

The Bargo MCP server

Give Claude, ChatGPT, Cursor, Codex or any Model Context Protocol client live stock-market intelligence: real-time quotes, options flow, analyst sentiment, fundamentals, insider and congressional trades, 13F holdings, prediction markets, and AI-infrastructure signals — from one endpoint your agent can query.

Get your free API key → See the setup
POST https://www.bargo.ai/mcp · Authorization: Bearer <your-key>
What is MCP?

The Model Context Protocol, in one paragraph

MCP is an open standard that lets an AI agent call structured, typed tools instead of guessing from scraped web pages. An MCP server publishes those tools; the model connects once and can then fetch exactly the data it needs, on demand. The Bargo MCP server turns dozens of market-data sources into a single set of tools any MCP-compatible model can call — so your agent reasons over live, structured finance data rather than stale text.

What your agent can query

One endpoint, dozens of market-data tools

A sample of the typed tools the Bargo MCP server exposes. Your model picks the right one per question, then computes over the results.

Prices & technicals

Real-time quotes, daily bars, indicators and symbol info.

get_quoteget_daily_barsget_technicals

Options flow

Unusual activity, full chains, positioning and LEAPS.

get_options_flowget_options_chainget_options_positioning

Sentiment & news

Article sentiment, trending headlines and authority-handle discussion.

get_news_feedget_news_sentimentget_ticker_sentiment

Fundamentals & valuation

Financials, analyst ratings, earnings calendar and corporate events.

get_fundamentalsget_analyst_ratingsget_earnings_calendar

Smart money

Insider open-market trades, 13F institutional holdings, and Congress trades.

get_insider_tradesget_fund_holdingsget_politician_trades

AI infrastructure

GPU spot pricing, compute economics and inference economics.

get_spot_pricingget_compute_economicsget_inference_economics

Market structure & flow

Microstructure, signed order flow, algo distribution and correlations.

get_market_structureget_signed_flowget_correlation_buckets

Prediction & research

Polymarket odds, deep context search and raw SQL over the dataset.

get_polymarketfind_market_contextquery_readonly_sql
Step 1

Get your MCP API key

Sign in to the dashboard with Google or an email link. Your key (a swmcp_… token) appears under API key — copy it once, then paste it into any config below. It authenticates every call your agent makes.

Your key
Dashboard → API key → Copy · or in the app: Account → MCP server → Copy
Get your key →
Step 2 · Two minutes to connect

Drop the config into your client

Pick your client below and paste the snippet, replacing YOUR_KEY with the key from your dashboard. Your agent can then query every source Bargo tracks.

claude_desktop_config.json
{
  "mcpServers": {
    "swiftalerts": {
      "type": "http",
      "url": "https://www.bargo.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}
~/.codex/config.toml
# OpenAI Codex CLI
[mcp_servers.swiftalerts]
url = "https://www.bargo.ai/mcp"
http_headers = { Authorization = "Bearer YOUR_KEY" }
Claude app · ChatGPT app — connector URL
# Consumer apps take a URL but no header — the key rides in the URL.
# Claude app:  Settings → Connectors → Add custom connector
# ChatGPT app: Settings → Connectors → Developer mode → Add (Auth: None)
https://www.bargo.ai/mcp?token=YOUR_KEY
mcp.json
# Cursor, Gemini CLI & most MCP clients
{
  "mcpServers": {
    "swiftalerts": {
      "url": "https://www.bargo.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}
streamable-http
# Raw — Streamable HTTP, POST /mcp
curl -X POST https://www.bargo.ai/mcp \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'

Your personal key and a ready-to-paste config live in the dashboard.

Compatibility

Works with any MCP client

If it speaks the Model Context Protocol over Streamable HTTP, it works with Bargo. Popular ones:

Claude DesktopClaude appChatGPT appCursor OpenAI Codex CLIGemini CLIClineContinue WindsurfAny custom MCP client
FAQ

Common questions about the Bargo MCP server

What is an MCP server?

An MCP (Model Context Protocol) server is a standard endpoint that gives AI agents like Claude and ChatGPT structured, real-time tools and data. Instead of scraping the web, the model calls typed tools over the protocol. The Bargo MCP server exposes live stock-market and AI-infrastructure data as those tools.

How do I connect Claude or ChatGPT to live stock market data?

Get a free Bargo API key from the dashboard, then add the endpoint https://www.bargo.ai/mcp with your key. In the Claude or ChatGPT app, add it under Settings → Connectors as a custom connector URL. In Claude Desktop, Cursor, Codex or Gemini, paste the config from the setup section above into your mcp.json.

Is there a free MCP server for stock market data?

Yes — Bargo is free while in beta. Sign in at the dashboard to generate an API key and connect any MCP client.

What data does the Bargo MCP server provide?

Real-time quotes and technicals, options flow and positioning, analyst sentiment and news, fundamentals and valuations, insider trades, congressional trades, 13F institutional holdings, prediction-market odds, market microstructure and signed flow, and AI-infrastructure signals such as GPU spot pricing and compute economics.

Where do I get my MCP token or API key?

Sign in at bargo.ai/dash with Google or an email link. Your swmcp_ API key is shown under the API key section — copy it once and paste it into your MCP client config or connector URL. You can regenerate it anytime.

Do I have to write code to use it?

No. Use it code-free in the Bargo Analyst app (web or desktop), or connect it as a no-code connector in the Claude and ChatGPT apps. Developers can also point Cursor, Codex, or a custom client at the same endpoint.