How to Use the Refiner MCP in Pydantic AI

Use Refiner with Pydantic AI for type-safe feedback workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Refiner MCP to Pydantic AI

Create your Vinkius account to connect Refiner 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 Refiner with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe feedback loops in Pydantic AI

Every call to `list_refiner_responses` is validated against your Pydantic schemas at runtime. If the survey data format changes, the agent stops immediately instead of processing bad input. This gives you total control over the data your agent sees. You define the model, and the server provides the data to fill it.

Manage contacts and segments in Pydantic AI

Call `get_refiner_contact` to retrieve user details that fit your strict type definitions. The agent won't hallucinate fields because the runtime validation catches any missing or mismatched data. Use `list_refiner_segments` to populate your agent's internal state. This keeps your user categorization logic predictable and easy to debug.

Verify server health with Pydantic AI

Execute `check_refiner_status` as a pre-flight check in your agent's toolset. This confirms the API is ready before the agent attempts to fetch or track sensitive feedback data. If the server isn't ready, the agent fails cleanly. This prevents downstream errors in your type-safe pipeline.

Setup guide

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

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

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

The framework automatically maps the JSON response from the server to your defined Pydantic models. Any field mismatch triggers a validation error before the agent can act on the data.

Yes, the server supports SSE and Streamable HTTP. Ensure your environment is configured for the transport you prefer when passing the toolset to the agent.

Yes. The toolset is model-agnostic. Whether you use a local LLM or a hosted provider, the validation layer remains consistent.

Your agent will raise a validation exception. This prevents the system from entering an unstable state caused by unexpected API changes.

The server handles all authentication via your Vinkius endpoint token. Data is only exchanged between your agent and the API, with no persistent storage occurring outside your runtime.

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