Compatible with every major AI agent and IDE
What is the IBKR (Interactive Brokers) MCP Server?
Connect your Interactive Brokers account to any AI agent to automate your trading workflows and portfolio monitoring through the Client Portal API.
What you can do
- Order Management — Place, modify, and cancel orders for specific accounts using natural language commands.
- Market Data — Fetch real-time snapshots for specific contracts (ConIds) to inform your trading decisions.
- Portfolio Tracking — Monitor cash balances by currency and view comprehensive account summaries including equity and margin metrics.
- Advanced Reporting — Programmatically request and retrieve pre-configured Flex Query reports for deep financial analysis and auditing.
- Session Maintenance — Keep your API session active with built-in session management tools.
How it works
- Subscribe to this server
- Enter your IBKR Client Portal API URL and your optional Flex Web Service Token
- Start managing your brokerage account from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Active Traders — execute and modify orders quickly without switching between complex trading interfaces
- Financial Analysts — automate the retrieval of portfolio ledgers and Flex statements for reporting
- Developers — integrate real-time market data and account management directly into your coding environment
Built-in capabilities (9)
Cancel an existing order
Get account summary
Retrieve a generated Flex Query report
Get market data snapshot for contracts
Get portfolio ledger
Modify an existing order
Requires a JSON array of order objects. Place a new order
Returns a ReferenceCode to be used with get_flex_statement. Generate a Flex Query report
Maintain Client Portal API session
Why Pydantic AI?
Pydantic AI validates every IBKR (Interactive Brokers) tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your IBKR (Interactive Brokers) integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your IBKR (Interactive Brokers) connection logic from agent behavior for testable, maintainable code
IBKR (Interactive Brokers) in Pydantic AI
IBKR (Interactive Brokers) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect IBKR (Interactive Brokers) to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for IBKR (Interactive Brokers) in Pydantic AI
The IBKR (Interactive Brokers) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 9 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
IBKR (Interactive Brokers) for Pydantic AI
Every tool call from Pydantic AI to the IBKR (Interactive Brokers) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I prevent my IBKR API session from timing out?
You can use the tickle_session tool. It is designed to maintain the Client Portal API session by sending a heartbeat, preventing timeouts due to inactivity.
Can I retrieve historical trade reports through this server?
Yes. First, use send_flex_request with your Flex Query ID to generate a report. Then, use the returned Reference Code with get_flex_statement to download the data.
How do I check my current buying power and margin requirements?
Use the get_account_summary tool with your Account ID. It returns a comprehensive summary of equity, margin, and other key financial metrics for the specified account.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your IBKR (Interactive Brokers) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
MeetingPulse
10 toolsInteractive audience engagement via MeetingPulse — track polls, Q&As, and meeting analytics.

pgvector (Vector Database)
6 toolsRun vector similarity searches, manage embedding tables, and build AI-powered retrieval pipelines — all directly inside your existing PostgreSQL database.

Mattermost (Secure Team Collaboration)
10 toolsManage team collaboration via Mattermost — send messages, search channels, and audit team activities.

Data.gov
13 toolsSearch 300,000+ US government open datasets — agriculture, climate, education, health, finance and more.
