How to Use the Addepar MCP in AutoGen

Q: How do I configure Addepar MCP tools in AutoGen?

Use mcpservertools with a StreamableHttpServerParams pointing to your endpoint. Pass the resulting list directly into your AssistantAgent constructor.

Give your AutoGen agents access to live wealth management data via the Addepar 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 Addepar MCP to AutoGen

Create your Vinkius account to connect Addepar to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen agents debate Addepar MCP Server data

Complex investment portfolios require multiple sets of eyes to manage effectively. You spin up a risk-analysis agent and a growth-focused agent, handing both of them access to `get_portfolio_analytics` via MCP tools. They pull the exact same performance numbers but evaluate them from completely different angles. The risk agent flags volatility in the returns, while the growth agent argues for holding the aggressive positions. They negotiate back and forth in the console until they reach a consensus on whether the client needs rebalancing.

Audit cash flows with competing perspectives

Reviewing account history is rarely a straightforward task. One agent runs `list_transactions` to compile a ledger of recent activity for a specific entity. A secondary compliance agent immediately reviews that output to spot unusual patterns or large withdrawals. If the compliance bot sees something weird, it demands the first agent pull more context using `get_entity_details`. This autonomous cross-checking catches anomalies a single human reviewer might miss after staring at spreadsheets all day.

Dissect holdings through collaborative review

Asset allocation decisions demand intense scrutiny. Your system uses `list_entities` to find a target account, then triggers `get_position_details` to map out every stock and bond inside it. A tax-optimization agent looks at the unrealized gains, while a macro-strategy bot evaluates sector exposure. They trade messages proposing different sell-offs, eventually handing the human advisor a fully vetted trade list.

Setup guide

Set up Addepar MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Addepar tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Addepar_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Addepar data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Addepar_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Addepar data")
    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 AutoGen

Use mcp_server_tools with a StreamableHttpServerParams pointing to your endpoint. Pass the resulting list directly into your AssistantAgent constructor.

Yes. You define the tools once and assign them to whichever agents need financial data access. They share the underlying HTTP transport automatically.

The McpToolAdapter handles the schema conversion. Your bots read the tool descriptions and figure out exactly what IDs or date ranges they need to provide.

That is exactly why you build multi-agent setups. A secondary critic agent reviews the first bot's math against the raw JSON output and corrects any hallucinated figures.

Vinkius operates a strict zero-trust sandbox. The specific asset positions, trade histories, and client entity names your bots debate remain entirely private. The execution environment is ephemeral and leaves no trace on our servers.

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