How to Use the lemon.markets MCP in Pydantic AI

Q: How do I initialize the lemon.markets MCP toolset in Pydantic AI?

Use the unified MCPToolset class pointing to the streamable HTTP endpoint for the lemon.markets MCP Server. Note that the older MCPServerHTTP class is deprecated and should not be used in Pydantic AI.

Build type-safe European trading bots using Pydantic AI to validate every lemon.markets stock quote and order.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect lemon.markets MCP to Pydantic AI

Create your Vinkius account to connect lemon.markets 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 lemon.markets with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Order Execution with Pydantic AI

The `place_new_order` tool passes trade parameters through Pydantic AI's strict runtime validation layer to ensure your buy and sell limits are perfectly formatted for lemon.markets. If the model attempts to pass an invalid volume or price, Pydantic AI blocks the call before it hits the API. After validation passes, the Pydantic AI agent calls `activate_pending_order` to execute the trade safely on lemon.markets. Using an MCP Server keeps your execution code clean and separated from validation schemas.

Runtime Validation for Market Data

Calling `get_latest_quote` returns real-time pricing data from lemon.markets that Pydantic AI instantly parses into typed Python models. If the brokerage API returns unexpected null fields or modified schemas, Pydantic AI raises a validation error immediately. This strict schema enforcement protects your Pydantic AI trading algorithms from running calculations on corrupted price data. The agent can then use `search_market_instruments` to find alternative assets with complete, valid data profiles on lemon.markets.

Portfolio Audits without Hallucinations

The `list_active_positions` tool pulls your live portfolio holdings from lemon.markets and validates the asset list against your local Pydantic AI models. The framework maps these incoming MCP payloads directly to your defined types, preventing your agent from trading hallucinated assets. To double-check your current exposure, the Pydantic AI agent cross-references these positions with `get_brokerage_account` and `list_brokerage_orders`. This multi-step validation loop keeps your local Pydantic AI state perfectly synchronized with the lemon.markets broker.

Setup guide

Set up lemon.markets 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": {
        "lemonmarkets-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent lemon.markets 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 lemon.markets. 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 lemon.markets 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 lemon.markets MCP in Pydantic AI

The Pydantic AI framework immediately raises a validation error at runtime. This prevents your agent from executing trades based on corrupted lemon.markets quotes or incomplete portfolio states.

Use the unified `MCPToolset` class pointing to the streamable HTTP endpoint for the lemon.markets MCP Server. Note that the older `MCPServerHTTP` class is deprecated and should not be used in Pydantic AI.

Yes, because the Pydantic AI framework is model-agnostic, you can route your trading logic through local models while still enforcing strict type validation on lemon.markets tools like `place_new_order`.

Yes, the lemon.markets MCP Server runs as an external process, and your Pydantic AI application connects to it using either streamable HTTP or SSE transports.

All financial data is routed through isolated V8 sandboxes that handle lemon.markets authentication via a single-use token. No portfolio details or brokerage credentials are ever written to disk or exposed to the LLM provider during Pydantic AI runs.

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