How to Use the Envoy MCP in Pydantic AI

Q: Can Pydantic AI manage package deliveries using Envoy?

Yes. Your agent can call listdeliveries to get a structured list of packages. The returned data is validated against Pydantic models before your agent processes it.

Bring type-safe office management to your Pydantic AI agents with Envoy tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Envoy MCP to Pydantic AI

Create your Vinkius account to connect Envoy 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 Envoy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Envoy desk bookings with Pydantic AI

The `reserve_desk` tool stops silent failures when booking office space. Your Pydantic AI agent reserves desks and handles `cancel_desk_reservation` while validating every input field against strict Python schemas at runtime. If the Envoy API returns unexpected fields, your agent raises a validation error immediately. This keeps your physical office database clean and free of corrupt reservation records.

Pre-register guests with strict type-safety

The `pre_register_visitor` tool ensures all visitor invitations conform to your exact data models. Your agent calls the registration tool and checks the output against your custom Pydantic schemas before confirming the guest. You can also query `list_visitors` to parse incoming guest lists into strongly-typed Python objects. This prevents your agent from hallucinating visitor details or processing broken payloads.

Track office stats via Envoy MCP Server

The `get_capacity` tool monitors your physical workspaces without worrying about API schema changes. The server lets your agent call live capacity statistics and retrieve employee sign-ins with `get_employee_signins`. Every sign-in record is parsed directly into a type-safe model. Your agent can confidently make scheduling decisions based on guaranteed data structures.

Setup guide

Set up Envoy 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": {
        "envoy-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the unified MCPToolset class pointing to your Envoy server URL. Pass this toolset directly into your Agent constructor to expose tools like `list_rooms` to your model.

The framework raises a validation error instantly instead of letting your agent make decisions on corrupt data. This is crucial when verifying physical desk availability via `list_desks`.

Yes. Your agent can call `list_deliveries` to get a structured list of packages. The returned data is validated against Pydantic models before your agent processes it.

Yes. The unified MCP toolset expects the server to be running externally. You connect to it using the streamable HTTP or SSE transport options.

Real-time capacity figures and employee sign-in records are processed inside an isolated Vinkius MCP sandbox. Your API credentials are never exposed to the LLM or any external logging service.

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