How to Use the Arcadia Plug MCP in Pydantic AI

Q: How do I integrate Arcadia Plug with Pydantic AI?

Install pydantic-ai-slimmcp first. Create an MCPToolset pointing to your Vinkius HTTP endpoint, then pass it as a list to the toolsets parameter in your Agent.

Q: Can Pydantic AI handle the Arcadia Plug server running remotely?

Yes, the unified MCPToolset supports remote HTTP endpoints. You just point it at the hosted Vinkius URL and let the framework handle the transport layer.

Build strict, type-safe utility tracking agents with Pydantic AI and Arcadia Plug.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arcadia Plug MCP to Pydantic AI

Create your Vinkius account to connect Arcadia Plug 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 Arcadia Plug with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Force strict validation on Arcadia Plug

Utility APIs often return messy, unpredictable JSON structures. When your agent calls `get_statement`, Pydantic AI validates the response against your defined models before proceeding. If the statement data is missing a required field, the framework fails loudly. Your agent won't hallucinate a billing amount just because the API returned a null value.

Track utility meters across any LLM

Being model-agnostic means you aren't locked into a single provider. You can use OpenAI to query `list_meters` today and switch to a local model tomorrow without changing the tool code. This MCP Server handles the actual data extraction from the utility provider. Your application just receives clean, validated Python objects ready for processing.

Audit login credentials safely

Managing access to multiple utility portals is a high-risk operation. Running `list_credentials` pulls your stored logins so your agent can map out what accounts it can reach. You can then chain this with `get_account_check` to verify access. Because Pydantic AI enforces types at runtime, you know exactly what credential format the agent is passing around.

Setup guide

Set up Arcadia Plug 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": {
        "arcadia-plug-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Arcadia Plug 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 Arcadia. 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 Arcadia Plug 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 Arcadia Plug MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` first. Create an `MCPToolset` pointing to your Vinkius HTTP endpoint, then pass it as a list to the `toolsets` parameter in your Agent.

Native tool calling often leads to silent failures. This framework guarantees that the utility data pulled from `list_statements` matches your exact schema requirements before the LLM even sees it.

Yes, the unified `MCPToolset` supports remote HTTP endpoints. You just point it at the hosted Vinkius URL and let the framework handle the transport layer.

Any model supported by the framework works perfectly. You can swap between Claude, Gemini, or local open-source models while keeping the exact same tool definitions.

We operate a strict zero-trust architecture. When your agent fetches sensitive utility account details, the operation happens inside an isolated V8 container that cannot access anything outside its specific execution context.

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