How to Use the Determ MCP in Pydantic AI

Build type-safe media monitoring agents with Pydantic AI and Determ.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Determ MCP to Pydantic AI

Create your Vinkius account to connect Determ 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 Determ with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict runtime validation with this MCP Server

Your agent uses the `list_media_mentions` tool to pull massive, nested JSON payloads of PR hits. When you connect this MCP Server to Pydantic AI, every single response gets validated against your predefined models. The framework ensures the data matches your exact schema. Silent failures ruin production systems. If the agent runs `get_mention_details` and the API returns a missing author field, Pydantic AI fails loudly. You catch the validation error immediately instead of passing hallucinated data to your PR team.

Type-safe sentiment tracking

Your agent executes the `list_monitoring_queries` tool to pull active topics, and Pydantic AI verifies the query IDs are actual integers. You get total confidence in the inputs before the agent does any real work. Bad data gets rejected instantly. For actual analysis, the agent calls `get_query_sentiment_summary`. The framework guarantees the positive, neutral, and negative scores sum up correctly based on your model constraints. No more LLMs making up math.

Model-agnostic media intelligence

The agent runs the `list_analytics_reports` tool to grab available dashboard layouts, regardless of which LLM you use. Pydantic AI enforces the structure. You can swap between different model providers while keeping the exact same toolset. Finding the loudest voices in your industry requires precise data. The agent triggers `list_top_media_sources` to identify high-volume publishers. Because the framework strictly types the output, your downstream code can safely map those publishers to your CRM records.

Setup guide

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

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

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

Install the pydantic-ai-slim package with MCP support. Create an MCPToolset pointing to your Vinkius HTTP endpoint, then pass it to your Agent's toolsets array to start the MCP Server.

The framework throws a strict validation error. If a tool like get_account_metadata returns a string instead of an expected integer for your API limit, the agent stops execution immediately.

Yes, the framework is completely model-agnostic. You can run a local Llama instance to process the mentions while still using the external Vinkius server for data retrieval.

It validates everything. Before the agent can even execute search_mentions_by_keyword, Pydantic AI checks the requested keyword string against your defined input schema.

The server handles sensitive brand mentions, sentiment scores, and competitor tracking data. Vinkius routes these requests through an isolated, ephemeral sandbox that leaves zero trace of your queries once the connection drops.

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