How to Use the Addepar MCP in LangChain

Build financial reasoning pipelines connecting the Addepar MCP Server to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Addepar MCP to LangChain

Create your Vinkius account to connect Addepar 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 Addepar with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Addepar MCP Server operations

ReAct agents shine when they can pull a thread through your wealth management data. You hand your LangChain setup a client name, and it runs `list_entities` to grab the internal ID. The output feeds straight into `get_entity_details` to pull their account structure without you writing a single glue script. That same agent decides to hit `get_portfolio_analytics` if the user asks about recent performance. LangSmith tracks every jump between tools, showing exactly how many tokens your financial queries consume and how long the underlying API takes to respond.

Trace cash flows and asset positions

Wealth managers need to know where the money moved before they advise a client. Using `list_transactions`, your graph fetches the historical buys and sells for a specific entity. It maps those moves against current holdings pulled via `get_position_details`. Building this logic into a custom chain lets you automate weekly portfolio reviews. The code just defines the sequence, while the LLM interprets the raw financial data and outputs a digestible summary for the advisor.

Combine financial data with external APIs

Portfolios do not exist in a vacuum. You might want to pull a client's holdings and compare them against breaking market news. The agent grabs the current state from Addepar, then queries a separate web-search tool to find related earnings reports. Because everything runs through standard MCP adapters, mixing these sources takes minutes instead of weeks. Your pipeline handles the financial math on one side and the qualitative research on the other.

Setup guide

Set up Addepar 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 Addepar 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({
    "addepar-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 Addepar 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 Addepar. 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 Addepar 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 Addepar MCP in LangChain

Install the adapters package. Initialize a MultiServerMCPClient pointing to the Vinkius endpoint, call get_tools(), and pass the array directly to your ReAct agent.

Yes. You define the schedule and the prompt. The agent sequences the necessary calls to fetch the data and formats the final document.

LangSmith handles that out of the box. Every call to the wealth management endpoints gets logged with exact timing and token counts.

Your agent reads performance metrics, asset positions, and historical trades. It uses the exact same permissions as your underlying API token.

Vinkius runs this integration inside an ephemeral V8 Isolate Sandbox. Your client account details, portfolio holdings, and trade history pass directly to your AI without touching our disks. The environment destroys itself the moment the session ends.

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