How to Use the Finnhub MCP in LangChain

Q: Can my LangChain agent search for tickers using Finnhub?

Yes. Your agent calls the searchsymbols tool to resolve company names to tickers. Once it finds the correct ticker, it passes that string to getcompanyprofile in the next step of the chain.

Get real-time stock and crypto data directly inside your LangChain pipelines using this managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finnhub MCP to LangChain

Create your Vinkius account to connect Finnhub to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Finnhub with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Finnhub data across LangChain pipelines

The `get_company_profile` tool extracts corporate metadata to seed your multi-step financial research chains. Your agent runs this first, grabs the ticker, and feeds it directly into `get_basic_financials` to pull debt-to-equity ratios without manual intervention. This sequential flow lets your LangChain agent decide which financial metrics to fetch next based on previous tool outputs. You get full visibility into every step of the chain through LangSmith tracing, showing exact latencies for each API call.

Feed live price quotes to LangChain agents

The `get_stock_quote` tool pulls real-time price metrics to feed active trading loops. Your agent checks the current price and immediately triggers `get_market_news` to fetch relevant articles if the stock drops more than three percent. Instead of relying on stale cache files, your LangChain chain evaluates current market conditions dynamically. This setup ensures your automated trading logic operates on live market data rather than historical averages.

Map digital assets inside LangChain memory

The `list_crypto_symbols` tool pulls valid trading pairs from specified digital asset exchanges. Your agent processes this list and runs `search_symbols` to match crypto tickers with traditional equity symbols in the same chain. You build LangChain agents that automatically update their internal reference tables with new crypto listings. The agent maps these assets dynamically, ensuring your portfolio tracking chains never miss a newly supported token.

Setup guide

Set up Finnhub MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Finnhub tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "finnhub-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Finnhub transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Finnhub. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Finnhub now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Finnhub MCP in LangChain

You load the tools using the LangChain MCP adapter and pass them directly to your agent constructor. The agent uses the `get_stock_quote` tool to fetch live prices and then decides whether to call `get_basic_financials` based on the user's prompt.

Yes. Your agent calls the `search_symbols` tool to resolve company names to tickers. Once it finds the correct ticker, it passes that string to `get_company_profile` in the next step of the chain.

You configure rate limits within your LangChain runnable configuration or handle them at the Vinkius gateway level. If an agent hits a limit while calling `get_market_news`, the chain catches the error and retries after a cooldown.

You pass the entire suite of tools to your agent. The agent executes `get_company_profile` to pull basic data and then immediately invokes `get_basic_financials` to run valuation calculations.

Vinkius runs this MCP Server in an isolated, zero-trust sandbox. Your stock tickers, financial queries, and API keys are never stored or exposed to external networks during execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript