How to Use the Assembled MCP in Pydantic AI

Q: How do I check for valid credentials in my script?

Trigger getaccountcheck as the first step in your agent's workflow. This validates the auth token before attempting more complex queries.

Give your Pydantic AI agents type-safe access to Assembled workforce data without silent failures or hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Assembled MCP to Pydantic AI

Create your Vinkius account to connect Assembled 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 Assembled with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict types on agent states

Workforce management APIs return complex nested objects that confuse standard agents. Pydantic AI validates every response from `list_agent_states` at runtime. If the API changes or returns weird data, the system fails loudly. You never have to worry about silent corruption ruining your routing logic. Calling `get_account_check` confirms the connection is valid before the agent even attempts to parse state data. That strictness keeps production systems reliable.

Parse schedules with Pydantic AI

Shift planning requires absolute precision. When your agent runs `list_schedules`, the resulting timeline maps directly to your predefined Python models. It rejects hallucinated fields instantly. Combining this with `list_users` gives you a validated list of available personnel. The MCP protocol handles the transport while Pydantic guarantees the structure. You get exactly what you expect.

Connect forecasting to any model

Because this framework is model-agnostic, you can swap between OpenAI, Anthropic, or local models without rewriting your tool logic. They all pull expected ticket volume via `list_forecasts` the exact same way. Checking `list_queues` lets the agent compare forecasted volume against current backlogs. Setup requires passing the unified MCPToolset to your Agent definition. The external MCP Server handles the rest over Streamable HTTP.

Setup guide

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

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

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

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass it inside the toolsets list when defining your Agent. Do not use the deprecated MCPServerHTTP method.

Pydantic AI throws a validation error immediately after calling `list_teams`. The agent stops execution rather than making decisions based on malformed data.

Yes. Since the framework is model-agnostic, your local model can execute `list_queues` just like a hosted one. The runtime validation protects weaker models from hallucinating tool outputs.

Trigger `get_account_check` as the first step in your agent's workflow. This validates the auth token before attempting more complex queries.

Employee names and shift times pass through a zero-trust V8 isolate. Vinkius processes the payload ephemerally and destroys the sandbox instantly. Your workforce data never touches persistent storage.

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