// langchain integration

Market data tools for
LangChain agents.

TickerAPI provides pre-computed financial context as MCP tools. LangChain's MCP adapter converts them into native LangChain tools — your agent gets market data with zero custom integration code.

try for free read the docs

// setup

Connect in one code block.

Use langchain-mcp-adapters to connect TickerAPI's remote MCP server to your LangChain agent. Every TickerAPI tool becomes a native LangChain tool automatically.

python

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-sonnet-4-20250514")

async with MultiServerMCPClient(
    {
        "tickerapi": {
            "url": "https://mcp.tickerapi.ai/",
            "transport": "streamable_http",
            "headers": {
                "Authorization": "Bearer tapi_your_api_key"
            },
        }
    }
) as client:
    agent = create_react_agent(model, client.get_tools())
    result = await agent.ainvoke(
        {"messages": "Is AAPL oversold right now?"}
    )

The MCP adapter discovers all available tools at connection time. No manual tool definitions needed.

// agent workflow

Multi-step analysis.

Your agent can chain tools — scan for oversold stocks, then get a full summary, then compare against peers. Each call returns categorical data the model understands without extra prompting.

python

result = await agent.ainvoke({
    "messages": "Find oversold tech stocks, then give me a detailed summary of the top pick and compare it against its main competitor."
})

agent internals

# Agent calls: scan_oversold(sector="Technology")
# → Returns list of oversold tech tickers

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

# Agent calls: compare_assets(tickers=["NVDA", "AMD"])
# → Side-by-side comparison across all dimensions

// state changes

Track state changes effortlessly.

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

python

result = await agent.ainvoke({
    "messages": "Check my watchlist for any state changes since yesterday."
})

json

{
  "ticker": "AAPL",
  "changes": [
    {
      "field": "rsi_zone",
      "from": "neutral",
      "to": "oversold"
    },
    {
      "field": "trend",
      "from": "uptrend",
      "to": "downtrend"
    }
  ]
}

// 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",
  "trend": "strong_uptrend",
  "momentum": {
    "rsi_zone": "overbought",
    "macd_signal": "bullish"
  },
  "volatility": "high",
  "fundamentals": {
    "pe_zone": "above_historical_avg",
    "earnings_surprise": "positive"
  }
}