How to Use the Massive MCP in LangChain

Feed historical dividend data directly into your LangChain agents for automated yield analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Massive MCP to LangChain

Create your Vinkius account to connect Massive 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 Massive with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Massive to your LangChain agents

Calling `list_dividends` inside a LangChain ReAct agent pulls raw payout histories straight into your working memory. Your agent grabs the ticker, fetches the exact cash dividend dates, and immediately pipes that array into the next link in your chain. Manual CSV exports from brokerages become obsolete. LangSmith tracks exactly how long the server takes to return those distribution records. Developers see the token usage for every fetch. If a specific ticker fails, the agent automatically retries or routes the error to a fallback prompt without breaking the entire pipeline.

Chain dividend histories into yield models

The `list_dividends` tool acts as the foundational MCP node for your financial chains. Once the agent retrieves the historical distributions, it passes the raw numbers directly to a math tool to calculate trailing yields. Automated workflows ingest a portfolio list and spit out complete income projections. Passing this data between nodes happens natively. Nobody writes custom API wrappers for financial endpoints anymore. The agent decides when it needs the payout history, requests it, and formats the final output based on your specific prompt instructions.

Build multi-step income analyzers

Triggering `list_dividends` establishes the baseline income facts before your agent does any heavy lifting. It retrieves the exact record dates and payment amounts for the requested equity. That structured output then feeds into a secondary agent connected to a vector store of earnings call transcripts. This setup lets you cross-reference hard financial payouts with executive commentary. The agent compares the actual cash distributed against the promises made by the board. Clients get a fully automated pipeline that flags discrepancies between what a company says and what it actually pays.

Setup guide

Set up Massive 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 Massive 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({
    "massive-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 Massive 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 Massive. 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 Massive 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 Massive MCP in LangChain

You initialize a MultiServerMCPClient with the endpoint URL. Then you call client.get_tools() and pass the resulting array directly into your create_agent setup.

Yes, LangSmith logs every interaction with the server. You can inspect the exact payload sent to the dividend endpoint and measure the latency of the response.

You absolutely can. Your agent fetches the payout records and immediately hands them to a SQL tool in the next chain step to insert the rows.

The server returns a clear error message to the agent. Because ReAct agents handle formatting errors natively, your setup automatically asks the user for the correct stock symbol.

The server only processes the specific ticker symbols you submit to fetch payment dates and dividend amounts. Vinkius runs the endpoint in an ephemeral V8 isolate sandbox, meaning your portfolio queries vanish the millisecond the connection closes.

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