How to Use the Collect MCP in Pydantic AI

Get type-safe data collection pipelines with Pydantic AI and the Collect MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Collect MCP to Pydantic AI

Create your Vinkius account to connect Collect 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 Collect with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate campaign data structures at runtime with Pydantic AI

Never let a corrupted API response break your production agent. When your Pydantic AI agent calls `get_campaign` or `list_campaigns`, the framework validates the incoming JSON against strict Python types, catching schema drift instantly. If the server returns an unexpected field format, the system raises a validation error immediately. This keeps your pipeline predictable, ensuring you never write broken campaign structures to your database.

Type-safe request generation and messaging

Sending requests to clients requires exact data shapes. Use `create_request` to build new forms, and let your agent verify that every required field is present before sending the dispatch signal. When follow-up is needed, the agent runs `send_message` to nudge the recipient. Because the payload is backed by Pydantic models, you can guarantee that message text and recipient IDs are formatted correctly every time.

Inspect element details with zero silent failures

Drill down into form fields using `get_element_details` and `get_request` without risking runtime crashes. This MCP integration ensures that if an agent tries to parse a missing field, the framework catches the discrepancy before your code acts on bad data. You can also query team environments using `get_team_info` and verify user permissions with `get_user_info`. Every returned object maps directly to a clean Python class, giving you full IDE autocompletion.

Setup guide

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

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

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

You use the MCPToolset class initialized with our hosted HTTP URL. Simply pass this toolset into your Agent constructor's toolsets list, and your agent can immediately invoke tools like `list_requests`.

Yes, the framework supports both Streamable HTTP and SSE. You can connect your type-safe agents to our hosted server using whichever transport matches your production network architecture.

The framework fails loudly by raising a validation error. Instead of your agent hallucinating or processing bad campaign details from `get_campaign`, the execution halts so your system can handle the error safely.

Yes. Because the framework is model-agnostic, you can run local models or commercial APIs. They will all be able to call tools like `list_messages` and `get_request` safely.

We secure your team info and user credentials using zero-trust architecture. The server runs inside an ephemeral sandbox that handles authentication via a single token, ensuring your credentials are never exposed to the underlying LLM.

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