// mcp integration

Market data tools for
any MCP client.

TickerDB exposes pre-computed financial data as MCP tools. Connect to Claude Desktop, Cursor, Windsurf, or any MCP-compatible client — your AI assistant pulls EOD market context directly from the chat.

try for free playground

// setup

Connect in two minutes.

Three ways to connect. Pick whichever fits your setup.

Option 1 — Claude.ai (OAuth)

Connect directly from Claude.ai once your access is enabled. No API key management — OAuth handles the rest via OAuth 2.1.

config

// Add as a Connector in Claude.ai
MCP server URL: https://mcp.tickerdb.com

// Authentication is handled automatically via OAuth
// No API key needed — connect when access opens

Uses OAuth 2.1 with PKCE. Your TickerDB session handles auth automatically.

Option 2 — Remote server (Bearer token)

Point any MCP client at the remote endpoint. No install needed. Pass your API key as a Bearer token in the authorization header.

config

// MCP server URL
https://mcp.tickerdb.com/mcp

// Authorization header
Authorization: Bearer tdb_your_api_key

Works with any client that supports remote MCP servers over HTTP.

Option 3 — npm package (stdio)

Run the MCP server locally via npx. Add this to your Claude Desktop config (or equivalent for your client):

json

{
  "mcpServers": {
    "tickerdb": {
      "command": "npx",
      "args": ["tickerdb-mcp"],
      "env": {
        "TICKERDB_KEY": "tdb_your_api_key"
      }
    }
  }
}

Runs locally over stdio. No network dependency beyond the TickerDB HTTP calls.

// multi-step analysis

Chain tools in one conversation.

Your MCP client can chain multiple tool calls in a single conversation. Pull a summary, check historical transitions, then monitor your watchlist — each call returns market-state data the model understands without extra prompting.

get_summary(ticker="AAPL")

Full categorical breakdown: trend, momentum, fundamentals

get_summary(ticker="AAPL", field="rsi_zone", band="deep_oversold")

Ticker event history with aftermath performance

get_watchlist()

Current state of all monitored tickers

get_watchlist_changes()

State changes across monitored tickers

The MCP client discovers all available tools at connection time. It picks the right tool for each step automatically.

// state changes

Track state changes effortlessly.

Most market data APIs return point-in-time snapshots. TickerDB tracks state transitions — your AI assistant sees what changed, not just what is.

json

{
  "timeframe": "daily",
  "run_date": "2026-03-28",
  "changes": {
    "AAPL": [
      {
        "field": "rsi_zone",
        "from": "neutral",
        "to": "oversold"
      },
      {
        "field": "trend_direction",
        "from": "uptrend",
        "to": "downtrend"
      }
    ]
  },
  "ticker_context": {
    "AAPL": {
      "last_changed_date": "2026-03-28"
    }
  },
  "tickers_checked": 2,
  "tickers_changed": 1
}

// what your assistant sees

What your assistant sees.

Every tool returns categorical facts — not raw OHLCV data. Your assistant can branch on "oversold" without needing to know what RSI > 70 means.

json

{
  "ticker": "NVDA",
  "data_status": "eod",
  "as_of_date": "2026-04-11",
  "trend": {
    "direction": "strong_uptrend",
    "ma_alignment": "aligned_bullish"
  },
  "momentum": {
    "rsi_zone": "overbought",
    "macd_state": "expanding_positive",
    "direction": "accelerating"
  },
  "volatility": {
    "regime": "normal",
    "regime_trend": "stable"
  },
  "fundamentals": {
    "valuation_zone": "fair_value",
    "pe_vs_historical_zone": "premium",
    "last_earnings_surprise": "beat"
  }
}