mcpField
B
Bullrundata Market Intelligence

Bullrundata Market Intelligence

Local
bullrundata.comFinance1Updated 6w ago

About Bullrundata Market Intelligence

Bullrundata Market Intelligence is an MCP server for investors and analysts seeking economic, market, institutional-positioning, and real-estate analysis. It combines tracked economic data with recession models and macro scenario cascades.

Key features

  1. 01Recession risk and macro indicators
  2. 02Sector rotation and institutional positioning
  3. 03Investment property and BRRRR analysis
  4. 04Economic time series and yield curves
  5. 05Macro catalyst cascade scenarios

Use cases

  1. 01Assess recession risk and market regime
  2. 02Compare cyclical and defensive sector signals
  3. 03Evaluate rental property deals
  4. 04Explore effects of macroeconomic catalysts

MCP support

Exposes market intelligence and economic analysis tools to MCP clients. It can run locally or connect through a hosted HTTP endpoint.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"market-intelligence": {
"command": "npx",
"args": [
"-y",
"@bullrundata/market-intelligence"
],
"env": {
"BULLRUNDATA_API_KEY": "<BULLRUNDATA_API_KEY>"
}
}
}
}
Run commandnpx -y @bullrundata/market-intelligence
Environment variables to set
BULLRUNDATA_API_KEYSecretYour BullrunData API key (get one free at bullrundata.com)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@bullrundata/market-intelligence0.1.2

Tools

27

Saved tool list · updated 3w ago

This tool takes no parameters.

Details

From the project README

Market Intelligence MCP Server

Recession probability, sector rotation, institutional positioning, macro cascade scenario analysis, real estate calculators, and real-time economic data — for Claude, ChatGPT, Cursor, and any MCP client.

Powered by the BullrunData API.

Quick Start (hosted — recommended)

The hosted endpoint at https://bullrundata.com/api/mcp is the fastest path. No install, auto-updates, and every MCP client below supports it natively.

Get a free API key at bullrundata.com — 100 calls/day, no credit card.

Claude Code
claude mcp add --transport http bullrundata https://bullrundata.com/api/mcp --header "Authorization: Bearer YOUR_API_KEY"
Cursor

Add to ~/.cursor/mcp.json (or the project-local .cursor/mcp.json):

{
  "mcpServers": {
    "bullrundata": {
      "url": "https://bullrundata.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
VS Code

Add to .vscode/mcp.json (workspace) or your user mcp.json:

{
  "servers": {
    "bullrundata": {
      "type": "http",
      "url": "https://bullrundata.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "bullrundata": {
      "serverUrl": "https://bullrundata.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Claude Desktop

Claude Desktop doesn't speak HTTP MCP natively yet — bridge via mcp-remote. Add to claude_desktop_config.json:

{
  "mcpServers": {
    "bullrundata": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://bullrundata.com/api/mcp",
        "--header",
        "Authorization: Bearer YOUR_API_KEY"
      ]
    }
  }
}

You can also skip the header entirely — on first connect, mcp-remote opens an OAuth flow in your browser and auto-provisions a free-tier key.

Local install (npm)

If you'd rather run the server locally (e.g. air-gapped environments, custom auth), install via npm:

Claude Desktop:

{
  "mcpServers": {
    "market-intelligence": {
      "command": "npx",
      "args": ["-y", "@bullrundata/market-intelligence"],
      "env": {
        "BULLRUNDATA_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code:

claude mcp add market-intelligence -- npx -y @bullrundata/market-intelligence

Set BULLRUNDATA_API_KEY in the environment where the command runs.

Available Tools

Macro Intelligence
ToolDescription
dashboard_summaryOne-call macro snapshot — recession probability, market regime, Fed stance, and key indicators
recession_probabilityProprietary recession probability model with confirmation layer
recession_indicatorsCurated key metrics block from the dashboard summary
fed_stanceCurrent Fed monetary policy stance and Fed funds rate
market_regimeMarket cycle phase (early / mid / late_cycle / recession)
confirmation_statusCoincident-indicator confirmation slice for the recession model
Markets & Institutional
ToolDescription
sectors_rotationRisk-on/risk-off signal from S&P sector performance (cyclical vs defensive) with leaders/laggards
sectors_flowsPer-sector accumulation and distribution signals
institutional_cftcAggregate institutional futures positioning across major contracts
cftc_contracts_listList available contracts for use with cftc_positioning_detail
cftc_positioning_detailPer-contract smart-money breakdown with week-over-week change
institutional_ticTreasury International Capital flows — net foreign Treasury demand
Real Estate Calculators
ToolDescription
investment_property_analysisRental property analysis: cap rate, DSCR, cash flow, 1% rule
brrrr_analysisBRRRR deal scoring (0-100) with 70% rule and full breakdown
Economic Data
ToolDescription
economic_indicatorTime series for any tracked indicator (VIXCLS, UNRATE, CPIAUCSL, T10Y2Y, etc.)
list_indicatorsList all tracked indicators, optionally filtered by category
interest_ratesFed Policy + Interest Rates categories
inflation_dataAll Inflation-category indicators
employment_dataLabor Market category (unemployment, payrolls, claims, JOLTS)
housing_dataHousing category (mortgage rates, starts, permits, prices)
yield_curve10Y-2Y and 10Y-3M spreads with inversion check
market_sentimentMarkets + Financial Conditions + Consumer Sentiment
Cascade Engine (Macro Scenario Analysis)
ToolDescription
cascade_listList all macro catalyst scenarios
cascade_analysisFull chain reaction for a catalyst with live data enrichment
cascade_searchSearch catalysts by keyword (e.g., "oil", "dollar", "china")
cascade_by_categoryFilter by category: geopolitical, monetary, credit, commodity, currency, structural

Available Catalysts: Oil Supply Shock, Dollar Liquidity Squeeze, Fed Emergency Rate Cut, US Recession, China-Taiwan Escalation, Yield Curve Inversion, Credit Market Freeze, EM Currency Crisis, Trade War Escalation, Sovereign Debt Crisis

Example Conversations

"What's the current recession risk?"

Claude uses recession_probability and returns:

Current recession probability is 37.9% (moderate risk). Fed stance: neutral. Market regime: mid-cycle. Recommendation: Mixed signals require caution. Begin defensive rotation.

"Is this a good time to buy an investment property at $450K?"

Claude uses investment_property_analysis + interest_rates:

At $450K with 20% down at 7%, monthly cash flow is $287. Cap rate: 5.3%. Cash-on-cash: 4.2%. DSCR: 1.18 (healthy). Current 30Y mortgage rate: 6.38%.

"What's the market risk-on/risk-off signal?"

Claude uses sectors_rotation + institutional_cftc:

Sector rotation signal: RISK_ON. Cyclical sectors leading, defensive lagging. Institutional positioning aligned risk-seeking. Playbook: stay overweight cyclicals, watch for rotation breakdown.

"What happens if oil hits $120?"

Claude uses cascade_analysis + sectors_rotation:

Oil Supply Shock cascade: Dollar demand surges (mechanical) -> Asian FX reserves drain (likely, weeks) -> Asian equity outflows (likely) -> Forced rate hikes in Asia (probable, months). Current sector rotation: RISK_ON, but energy sector lagging suggests market hasn't priced supply risk yet. Playbook: inflation hedges and cash reserves. Watch Fed swap line usage for systemic signal.

Configuration

For the hosted endpoint, authentication is passed as a Bearer header in your client config (see Quick Start above) or negotiated via OAuth on first connect — no environment variables needed.

For the local npx install:

Environment VariableRequiredDescription
BULLRUNDATA_API_KEYYesYour API key from bullrundata.com

Pricing

TierCalls/DayPrice
Free100$0
Pro10,000$29/mo
Business100,000$99/mo

Troubleshooting

Tools don't appear in Claude after install
  1. Confirm the MCP server is registered: in Claude Desktop, check Settings → Connectors (or Developer) for market-intelligence. In Claude Code, run claude mcp list.
  2. Restart Claude Desktop fully (quit, not just close window) — connector changes don't hot-reload.
  3. Verify your BULLRUNDATA_API_KEY env var is set and valid. Without it, tools fail at first call.
  4. If using the remote server (https://market.bullrundata.com/mcp) directly, complete the OAuth flow in your browser when prompted — Claude needs the bearer token before it can call tools.
401 Unauthorized from a tool

Your API key is missing, expired, or inactive. Get a fresh one at bullrundata.com/login. For the remote server flow, re-authenticate via the OAuth screen; the connector auto-provisions a free-tier key on first connect.

429 Too Many Requests

You hit your daily rate limit. Limits reset at 00:00 UTC.

TierLimit
Free100 requests/day
Pro10,000 requests/day
Business100,000 requests/day

Upgrade at bullrundata.com/pricing or wait for the UTC reset.

OAuth flow stuck or times out (remote server)

The remote server uses GitHub OAuth. If the redirect hangs:

  1. Confirm cookies and pop-ups are allowed for market.bullrundata.com and claude.ai
  2. Try authorizing in an incognito window (clears cached OAuth state)
  3. Check that https://market.bullrundata.com/.well-known/oauth-authorization-server returns 200 in your browser
First request is slow (~2–4 seconds)

Cold-start latency on the serverless deploy. Subsequent requests in the same session should respond in <500ms.

cascade_analysis returns "live data unavailable"

The cascade tool optionally enriches with live BullrunData market data. If the upstream API is briefly unreachable, you'll still get the full catalyst tree — only the live overlay is skipped. Pass include_live_data: false to skip the live fetch entirely.

Tool returns stale data

Economic indicators refresh multiple times daily. Check data_freshness in dashboard_summary for the last refresh timestamp.

Still stuck

Open an issue at GitHub Issues or email [email protected] with: tool name, full error message, and approximate timestamp.

Support

License

Elastic License 2.0 — see LICENSE.

You may use, modify, and redistribute this software. You may not offer it as a hosted or managed service that provides users with access to a substantial set of the features or functionality of the software.

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.