How to Use the Mainstay (AdmitHub) MCP in Pydantic AI

Pydantic AI meets Mainstay (AdmitHub) for type-safe student engagement and data integrity.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mainstay (AdmitHub) MCP to Pydantic AI

Create your Vinkius account to connect Mainstay (AdmitHub) 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 Mainstay (AdmitHub) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-validated student record access

Every response from `get_contact_details` is checked against your Pydantic models at runtime. If the data doesn't match your schema, the agent stops immediately. This prevents silent data corruption in your agent's logic. You get a clean, validated object every time your agent fetches student info.

Audit campaigns with strict schemas

Use `list_campaigns` to retrieve your outreach data with full type safety. The agent validates the incoming list against your defined model before proceeding. This ensures your agent is always working with accurate campaign structures. It eliminates the risk of hallucinated fields or missing data in your automated workflows.

Safe parsing of message logs

Your agent fetches historical data using `list_messages` and validates the results against your Pydantic model. This keeps your agent's state consistent. You avoid the common pitfalls of loosely typed API responses. Your agent's logic remains robust because it only operates on data that meets your exact requirements.

Setup guide

Set up Mainstay (AdmitHub) 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": {
        "mainstay-admithub-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Mainstay (AdmitHub) 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 Mainstay. 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 Mainstay (AdmitHub) 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 Mainstay (AdmitHub) MCP in Pydantic AI

Install the MCP toolset and initialize an MCPToolset with your server URL. Pass this into your agent's toolsets list to start using the validated tools.

Yes. If an API response fails validation against your Pydantic model, the agent will raise an error immediately. This stops the agent from acting on invalid data.

Absolutely. Because Pydantic AI is model-agnostic, you can connect your local model to these tools and still benefit from full type validation.

Vinkius handles the auth layer. Your agent connects through a secure HTTP transport, ensuring your session is ephemeral and isolated.

The server exposes contact details and campaign metadata. Every request is scoped to your specific endpoint, ensuring no other data is accessible.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python