// llamaindex integration

Financial context for
LlamaIndex agents.

TickerDB provides pre-computed market data as MCP tools that LlamaIndex agents can call directly. Categorical responses designed for how language models reason about financial data.

try for free playground

// setup

Four lines to market data.

Use llama-index-tools-mcp to connect TickerDB's remote MCP server. Every tool is available to your agent immediately.

python

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

mcp_client = BasicMCPClient(
    "https://mcp.tickerdb.com/mcp",
    headers={
        "Authorization": "Bearer tdb_your_api_key"
    },
)
mcp_tools = McpToolSpec(client=mcp_client)

tools = await mcp_tools.to_tool_list_async()

Pass tools to any LlamaIndex agent. Each tool maps to a TickerDB endpoint with typed parameters.

// agent workflow

Multi-step analysis.

Your agent can chain tools — get a full summary, check historical band transitions, then monitor watchlist changes. Each call returns market-state data the model understands without extra prompting.

python

from llama_index.core.agent import FunctionCallingAgent
from llama_index.llms.anthropic import Anthropic

agent = FunctionCallingAgent.from_tools(
    tools,
    llm=Anthropic(model="claude-sonnet-4-20250514"),
    verbose=True
)

response = agent.chat(
    "Get a summary of AAPL, check when it last entered deep oversold, and show any recent watchlist changes."
)

agent internals

# Agent calls: get_summary("AAPL")
# → Full categorical breakdown: trend, momentum, fundamentals

# Agent calls: get_summary("AAPL", field="rsi_zone", band="deep_oversold")
# → Historical band transitions for RSI entering deep oversold

# Agent calls: get_watchlist_changes()
# → State changes across monitored tickers

// state changes

Track state changes effortlessly.

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

python

response = agent.chat(
    "Check my watchlist for any state changes since yesterday."
)

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 agent sees

What your agent sees.

Every tool returns categorical facts — not raw OHLCV data. Your agent 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"
  }
}