How to Use the AEGIS Hedging MCP in Pydantic AI

Q: How do I add AEGIS Hedging to a Pydantic AI agent?

Install the MCP extras package and instantiate an MCPToolset with your Vinkius endpoint. Assign this to the toolsets list when defining your agent.

Q: Should I use MCPServerHTTP for this integration?

No, that class is deprecated. You must use the unified MCPToolset approach to connect external servers to your agent.

Build type-safe energy trading agents that validate AEGIS Hedging market data at runtime with 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 AEGIS Hedging MCP to Pydantic AI

Create your Vinkius account to connect AEGIS Hedging 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 AEGIS Hedging with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Energy Market Data

Financial agents cannot afford silent failures when parsing market prices. By running this MCP Server through your Pydantic framework, every forward curve gets validated against strict models before the agent acts on it. When the agent calls the `get_forward_curves` tool, Pydantic AI intercepts the response. If the API returns a string instead of a float for a price, the system fails loudly with a validation error rather than hallucinating a bad trade.

Validate MTM Valuations Instantly

Pulling mark-to-market data requires precision. Your application can use the `get_valuations` tool to fetch live portfolio values, knowing that the returned JSON must match your exact schema. Because the framework is model-agnostic, you can swap between Claude, OpenAI, or local models without rewriting your validation logic. The MCP integration ensures that whichever model you use, the valuation data structure remains consistent and predictable.

Connect Pydantic AI to AEGIS

Querying active energy hedges is straightforward when you use the unified toolset approach. Your agent executes `list_trades` to grab current positions, and you can map those directly to your internal Python objects. Install `pydantic-ai-slim[mcp]` and initialize `MCPToolset` with your Vinkius HTTP URL. Pass it to your Agent's `toolsets` parameter, and it will automatically run `check_api_version` to establish the connection via Streamable HTTP.

Setup guide

Set up AEGIS Hedging 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": {
        "aegis-hedging-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent AEGIS Hedging 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 AEGIS Hedging. 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 AEGIS Hedging 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 AEGIS Hedging MCP in Pydantic AI

Install the MCP extras package and instantiate an `MCPToolset` with your Vinkius endpoint. Assign this to the `toolsets` list when defining your agent.

The framework triggers a strict runtime validation error. If a tool like `get_valuations` returns a missing field, the agent stops immediately instead of processing corrupted financial data.

Yes. Pydantic AI is completely model-agnostic. As long as your local model supports tool calling, it can interact with the server to fetch forward curves and trade lists.

No, that class is deprecated. You must use the unified `MCPToolset` approach to connect external servers to your agent.

Your mark-to-market valuations and trade histories remain strictly confidential. Vinkius manages the authentication layer externally, meaning your API tokens never touch your application code or get exposed in logs.

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