How to Use the Addepar MCP in Pydantic AI

Q: How do I initialize the Addepar MCP Server inside Pydantic AI?

You import MCPToolset and pass the server HTTP endpoint URL. Then, you simply register this toolset in your Pydantic AI Agent constructor to expose tools like listentities.

Run type-safe financial operations by validating Addepar portfolio data through Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Addepar to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Portfolio Audits with Pydantic AI

The `get_portfolio_analytics` tool retrieves raw performance metrics and feeds them directly into your Pydantic AI validation engine. If the API returns a malformed date or an unexpected null value, the framework raises a validation error immediately. This strict validation prevents your agent from making decisions based on corrupted financial data. You get guaranteed type safety for every portfolio metric before your model even sees the payload.

Validated Position Queries via Pydantic AI

The `get_position_details` tool pulls live asset holding data into your Pydantic AI agent. The framework validates the returned asset classes, quantities, and market values against your strict Pydantic models. By ensuring the data schema matches your code expectations, you eliminate silent failures in your reporting pipeline. Your agent can confidently process complex asset allocations knowing the underlying data is clean.

Structured Transaction Parsing using MCP

The `list_transactions` tool exposes raw financial transaction histories to your Pydantic AI environment. Your agent uses this MCP integration to build structured tax reports or audit trails that match your exact schema definitions. Because this MCP Server integrates with Pydantic AI's model-agnostic architecture, you can swap your underlying LLM provider at any time. Your transaction data structure and validation rules remain completely unchanged.

Setup guide

Set up Addepar MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "addepar-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Addepar tools.",
)

result = await agent.run("List recent Addepar transactions")
print(result.output)

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 Pydantic AI

You import `MCPToolset` and pass the server HTTP endpoint URL. Then, you simply register this toolset in your Pydantic AI Agent constructor to expose tools like `list_entities`.

The framework catches the schema mismatch during runtime validation. Instead of passing bad data to your agent, Pydantic AI raises a clear validation error so you can handle the issue safely.

Yes, the framework supports both streamable HTTP and SSE transports. You can configure your MCP toolset to connect to our hosted server using whichever protocol fits your infrastructure.

Pydantic AI is completely model-agnostic. You can use the Addepar tools with local models, Anthropic, or OpenAI while maintaining the exact same runtime validation.

All data transit between Pydantic AI and the server is encrypted. The server processes your investment metrics and performance data ephemerally inside a zero-trust sandbox, never storing your financial records.

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