How to Use the IBKR (Interactive Brokers) MCP in Pydantic AI

Q: How do I configure Pydantic AI to work with IBKR (Interactive Brokers)?

Install pydantic-ai-slimmcp and initialize the MCPToolset with your Vinkius HTTP server URL. Pass this toolset directly into your Agent constructor to give your model type-safe access to the trading tools.

Q: Can I use Pydantic AI to modify open orders on IBKR (Interactive Brokers) safely?

Yes. You can use modifyorder within your agent's execution loop. The framework ensures that parameters like order ID, price, and quantity match the exact types required by the Client Portal API before making the call.

Q: Does this MCP setup support both HTTP and SSE transports?

Yes. The MCPToolset in Pydantic AI supports both Streamable HTTP and SSE transports, allowing you to connect to your Vinkius-hosted server using the protocol that best fits your infrastructure.

Build type-safe automated trading systems with Pydantic AI validating every IBKR order and ledger update at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBKR (Interactive Brokers) MCP to Pydantic AI

Create your Vinkius account to connect IBKR (Interactive Brokers) 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 IBKR (Interactive Brokers) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Order Execution with Pydantic AI

Silent data corruption is the enemy of automated trading. When your agent decides to execute a trade, Pydantic AI validates the structure of the payload before it ever reaches the MCP Server. The `place_order` tool requires a precise JSON array of order objects, which the framework verifies against strict type schemas. If the agent generates an invalid price format or missing contract ID, the system throws a runtime validation error instantly. This prevents malformed payloads from hitting the Client Portal API, saving you from costly execution errors or rejected orders.

Runtime Validation for Portfolio Ledgers

Financial reporting tools must be accurate down to the penny. By querying `get_portfolio_ledger` and `get_account_summary` through this type-safe framework, you guarantee that every balance, margin requirement, and currency field matches your expected data models. If IBKR updates its API response format or returns unexpected null values, Pydantic AI fails loudly. Instead of your agent making decisions based on parsed garbage, your system halts safely, protecting your capital from bad data.

Structured Market Data and Session Control

Fast-moving markets require reliable snapshots. Using this MCP Server, the agent calls `get_market_data_snapshot` to retrieve contract details, which are parsed directly into strongly-typed Python objects. This lets you write clean, autocompleted logic for processing bid/ask spreads. To keep the connection alive during long trading sessions, the framework runs background calls to `tickle_session`. If the session drops, your agent can catch the connection error, use `modify_order` or `cancel_order` to clean up open positions, and exit safely.

Setup guide

Set up IBKR (Interactive Brokers) 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": {
        "ibkr-interactive-brokers-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent IBKR (Interactive Brokers) 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 Interactive Brokers. 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 IBKR (Interactive Brokers) 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 IBKR (Interactive Brokers) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize the `MCPToolset` with your Vinkius HTTP server URL. Pass this toolset directly into your `Agent` constructor to give your model type-safe access to the trading tools.

The framework will raise a validation error at runtime. This strict validation prevents your trading agent from acting on corrupt or misaligned financial data, ensuring absolute correctness over silent failures.

Yes. You can use `modify_order` within your agent's execution loop. The framework ensures that parameters like order ID, price, and quantity match the exact types required by the Client Portal API before making the call.

Yes. The `MCPToolset` in Pydantic AI supports both Streamable HTTP and SSE transports, allowing you to connect to your Vinkius-hosted server using the protocol that best fits your infrastructure.

All session tokens and authentication headers are handled securely via Vinkius's single-endpoint token system. Your raw API credentials never pass through the client; they are injected directly inside the secure, ephemeral V8 isolate running your server.

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