How to Use the Relay Workflow Automation MCP in Pydantic AI

Execute type-safe Relay Workflow Automation tasks with runtime schema validation using the Pydantic AI framework via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Relay Workflow Automation MCP to Pydantic AI

Create your Vinkius account to connect Relay Workflow Automation to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Relay Workflow Automation with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate workflow schemas before execution

The `list_workflows` tool pulls your active Relay automations and validates their input schemas against Pydantic models before your MCP agent can run them. When you call `run_workflow`, the Pydantic AI framework ensures every input parameter matches the exact type expected by the Relay API. This strict validation prevents malformed JSON payloads from ever hitting your API endpoint. If your agent tries to pass a string where an integer is expected, the Pydantic AI framework raises a validation error immediately.

Monitor run states with strict type safety

The `get_run_status` tool fetches the live state of any active automation run and parses it into a typed Pydantic AI model. Your agent can check the state fields safely, knowing that the status strings, timestamps, and error messages are validated at runtime. By combining this tool with `list_runs`, your Pydantic AI agent builds a clean history of executions. If the Relay API returns an unexpected data structure, the system fails loudly instead of letting corrupted data pollute your database.

Cancel runs safely using this MCP Server

The `cancel_run` tool terminates active executions that fail to meet your operational constraints within the Pydantic AI framework. Your agent retrieves the workflow details with `get_workflow` to verify the run configuration before sending the cancellation command. Running this MCP Server with Pydantic AI guarantees that every tool call, from listing runs to stopping executions, adheres to strict Python type definitions. This eliminates silent failures and ensures predictable agent behavior in production.

Setup guide

Set up Relay Workflow Automation 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": {
        "relay-workflow-automation-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Relay Workflow Automation 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 Relay. 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 Relay Workflow Automation 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 Relay Workflow Automation MCP in Pydantic AI

Install the package with the mcp extra and initialize the toolset class. Pass the toolset instance directly into the toolsets argument of your Pydantic AI Agent to configure the MCP client.

The framework raises a validation error immediately. Because every response from tools is validated against Pydantic schemas, your agent never processes corrupted payloads.

Yes, the framework natively supports async executions. Your agent can trigger runs and poll their status without blocking your main application loop.

Pydantic AI is model-agnostic. You can use this server with OpenAI, Anthropic, Gemini, or any local model that supports tool calling.

Your Relay API tokens are stored in the Vinkius zero-trust environment. The schema data retrieved by the tools is validated in memory in your local Python process and is never exposed to external telemetry.

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