How to Use the Unanet MCP in Pydantic AI

Q: Can I use Pydantic AI to verify historical timesheets for Unanet clients?

Yes. The timesheets tool is available and its output will be strictly validated against your model. You get reliable data, period.

Get guaranteed accurate data reads from Unanet using 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 Unanet MCP to Pydantic AI

Create your Vinkius account to connect Unanet 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 Unanet with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify Project and User Data Integrity

Need to know what projects are active? The agent calls `projects` and validates the returned list against your defined schema. If the data is weird, it fails loud—you know exactly why. It also uses `users` to pull employee records, but everything goes through Pydantic validation first. You get guaranteed correct structures.

Schema-Validated Financial Reporting

When you run the `expenses` tool, your agent doesn't trust the API blindly. It validates every field in the expense report listing against a Pydantic model at runtime. This means no silent corruption. If Unanet sends unexpected data for an expense record, your process stops and tells you exactly what's wrong.

Reliable Timesheet Data Retrieval

The `timesheets` tool is available, but its output is locked down by type safety. You won't get hallucinated fields or unexpected data types when listing timesheets for a user. This level of correctness is critical when working with core Unanet time tracking and requires the agent to confirm every field before proceeding.

Setup guide

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

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

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

It validates every single MCP response against defined Pydantic models at runtime. If the API sends bad or unexpected data, the agent fails loudly with a clear validation error.

The main upside is guaranteed correctness. You don't risk silent failures or corrupted fields when your agent reads project details, user data, or expenses from the MCP Server.

Yes. The `timesheets` tool is available and its output will be strictly validated against your model. You get reliable data, period.

Yes, the server touches user identifiers, project metadata, time logs, and detailed expense records. All is subject to strict type-checking.

It doesn't care if you use OpenAI, Anthropic, or Gemini; it validates everything coming back from the MCP Server using your Python models. It makes the connection model-agnostic.

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