How to Use the Baseten MCP in Pydantic AI

Q: How do I configure the Baseten MCP Server with Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp". Create an MCPToolset with your HTTP endpoint and assign it to your Agent's toolsets array.

Connect Baseten to Pydantic AI to enforce strict type validation on every serverless inference prediction and deployment check.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to Pydantic AI

Create your Vinkius account to connect Baseten 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 Baseten with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Baseten Predictions

When your agent calls the `predict` tool, it has to formulate explicit tensor shapes or dictionaries that strictly match your deployed instance. Pydantic AI validates these payloads at runtime. If the agent tries to send hallucinated fields, the system fails loudly. Correctness matters more than speed when dealing with remote endpoints. This integration ensures that malformed inference requests never leave your system, saving you from silent corruption or wasted compute cycles.

Audit Models and Deployments via MCP Server

By invoking `get_deployment` and `list_models`, your agent retrieves explicit details about your running instances and managed models. Every response gets parsed through rigid schemas, guaranteeing your agent only acts on verified infrastructure data. You connect this setup by passing an `MCPToolset` to your Agent configuration. Because the framework is model-agnostic, you can use local models or external providers to run these checks.

Inspect Workspace Secrets Safely

Executing `list_secrets` pulls the names of your securely managed workspace secrets without ever showing the values. Your agent verifies the environment configuration while strict type enforcement guarantees no unexpected data leaks into the logs. Checking active inference bounds via `list_deployments` through this MCP integration works exactly the same way. The agent receives a validated list of active resources, allowing it to make deterministic routing decisions based on hard facts.

Setup guide

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

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

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

Install the slim package with `pip install "pydantic-ai-slim[mcp]"`. Create an `MCPToolset` with your HTTP endpoint and assign it to your Agent's toolsets array.

Yes, the framework checks every tensor shape and dictionary payload before execution. If the agent generates invalid parameters for the `predict` tool, the system throws a validation error immediately.

The framework is completely model-agnostic. You can use any supported provider to manage your deployments and run inference commands.

The system fails loudly with a Pydantic validation error. You never have to worry about silent corruption or your agent hallucinating deployment details.

The tool strictly lists secret names without returning their actual values. Vinkius handles the transport through a zero-trust, ephemeral V8 Isolate Sandbox, meaning your infrastructure metadata is never exposed to unauthorized endpoints.

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