How to Use the Conduit MCP in Pydantic AI

Add Conduit to Pydantic AI for type-safe control over your integration workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conduit MCP to Pydantic AI

Create your Vinkius account to connect Conduit 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 Conduit with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate workflow data in Pydantic AI

Every response from `get_workflow` is validated against Pydantic models at runtime. Your agent won't hallucinate field names because the schema is strictly enforced. If the API returns unexpected data, the process fails immediately. This ensures your agent only acts on accurate information about your integration state.

Execute triggers with Pydantic AI

Use `trigger_workflow` to initiate jobs knowing the inputs are type-checked. Your agent handles the result based on the defined model structures. It prevents malformed requests from hitting your platform. You gain confidence that every trigger call conforms to the expected API contract.

Audit your integrations with Pydantic AI

Use `list_workflows` and `list_workflow_runs` to inspect your history. Pydantic AI guarantees that the returned lists match the expected Python objects. This makes your integration monitoring logic predictable and clean. You can trust the data flowing into your agent's decision-making loop.

Setup guide

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

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

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

Install the slim package and pass the MCPToolset to your Agent. It handles the connection and provides type-safe access to all server tools.

Yes, it raises a validation error if the server output doesn't match your Pydantic models. This stops bad data from propagating through your agent logic.

It supports both Streamable HTTP and SSE. You just point the toolset to your endpoint and the framework handles the rest.

Since the framework is model-agnostic, you can swap between Anthropic, OpenAI, or local models without changing your tool definitions.

Your workflow logs are fetched over a secure, authenticated channel. We define strict schemas for these objects to prevent any accidental leakage of sensitive fields.

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