How to Use the DecileHub MCP in LangChain

Q: How do I connect the DecileHub MCP Server to a LangChain agent?

Install langchain-mcp-adapters. Initialize a MultiServerMCPClient pointing to the DecileHub endpoint. Call client.gettools() and pass that array right into your agent constructor.

Build multi-step reasoning chains in LangChain that query DecileHub fund performance and valuation data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DecileHub MCP to LangChain

Create your Vinkius account to connect DecileHub 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 DecileHub with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain DecileHub MCP Server tools

Connecting this MCP Server gives your LangChain agents direct access to private market data. You give them a goal, and they figure out the path. By attaching this server, your ReAct agent can pull a list of LPs using `list_investors` and immediately feed those IDs into `get_investor` to build a complete profile. Every step gets logged in LangSmith. You see exactly how many tokens the agent burned deciding between `get_fund` and `get_fund_performance`. If the chain breaks, you know exactly which tool failed.

Map portfolio valuations

This server lets your agent map out entire portfolios without manual data entry. Your agent pulls the raw data using `list_valuations` via the MCP connection and pipes it straight into your preferred reporting format. It grabs the parent fund context via `list_funds` in the same execution loop. The output of one tool drives the next. When `list_companies_by_fund` returns an array of startups, your LangChain pipeline iterates through them. It calls `get_company` for each entry, assembling a clear picture of the portfolio without human intervention.

Track SEC filings automatically

Automate your SEC compliance checks by giving your agent access to this server. The agent runs `list_filings` to spot new documents, then triggers `get_filing_report` to extract the actual text. You can wire this up to run on a schedule. The agent checks for updates, parses the regulatory text, and drops a summary into your database. Missed deadlines and ignored disclosures become a thing of the past.

Setup guide

Set up DecileHub 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 DecileHub 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({
    "decilehub-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 DecileHub 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 Decile Hub. 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 DecileHub 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 DecileHub MCP in LangChain

Install `langchain-mcp-adapters`. Initialize a `MultiServerMCPClient` pointing to the DecileHub endpoint. Call `client.get_tools()` and pass that array right into your agent constructor.

Yes. LangSmith automatically traces every interaction with the MCP protocol. You get full visibility into latency, token consumption, and the exact payloads sent to tools like `get_fund_performance`.

That is exactly what it is built for. The agent reads the tool descriptions and decides when to pull portfolio data versus investor metrics. It handles the decision logic entirely on its own.

The agent receives the error message and tries to correct its input. You can test this by running `check_decilehub_status` to verify connectivity before firing off complex queries.

Vinkius runs the server in an ephemeral V8 isolate sandbox. Your proprietary company valuations and LP details never touch local disk. The connection is stateless, meaning the environment dies the second your query finishes.

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