How to Use the Make (Workflow Automation) MCP in Pydantic AI

Q: How do I configure the Make (Workflow Automation) MCP Server with Pydantic AI?

Use the unified MCPToolset("http://...") setup. Pass it into your agent via the toolsets=toolset parameter. The older HTTP server classes are deprecated.

Q: What happens if Make (Workflow Automation) returns an unexpected log format to Pydantic AI?

The framework fails loudly. If listscenariologs returns data that doesn't match your Pydantic model, it throws a validation error. It never lets the agent guess the contents.

Q: How does the agent find the correct organization ID?

It executes listorganizations first to retrieve the authenticated user's details. It then uses that validated ID to query specific scenarios. Every step is type-checked at runtime.

Q: Are my connection credentials exposed to the LLM by this MCP Server?

No. The server reads connection metadata via listconnections but never exposes the underlying OAuth tokens. Your Pydantic models only receive the safe, structured metadata required for auditing.

Type-safe Make (Workflow Automation) MCP Server monitoring for Pydantic AI. Audit scenarios and validate logs with strict runtime checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Make (Workflow Automation) MCP to Pydantic AI

Create your Vinkius account to connect Make (Workflow Automation) 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 Make (Workflow Automation) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Make (Workflow Automation) MCP Server

Automation data is useless if the agent hallucinates the fields from `get_scenario`. Pydantic AI forces every response from the Make (Workflow Automation) MCP Server into a strict data model. If the API returns an unexpected structure, the framework throws a validation error immediately. This means you never get silent corruption in your monitoring pipelines. When your agent calls `list_scenarios`, it receives guaranteed, typed objects. You write your logic knowing the scenario IDs and execution statuses are exactly what the API sent.

Audit teams and organizations reliably

Mapping your automation environment requires exact identifiers from `list_organizations`. The agent fetches the root IDs, then passes them into `list_teams`. Every step of this chain is validated at runtime. You can swap out the underlying LLM without rewriting your monitoring logic. Whether you use Anthropic or local models, this MCP Server ensures the data returned from `list_connections` remains perfectly structured.

Debug logs and data stores

Reading error traces requires precision, so the agent pulls the exact error payload via `list_scenario_logs`. Because Pydantic AI validates the output, your debugging agent always gets the raw, untampered error message. The same applies to state management. Calling `list_data_stores` returns the schemas of your internal Make databases. You can build reliable monitoring tools that alert you the second a data store hits its capacity limit.

Setup guide

Set up Make (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": {
        "make-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 Make (Workflow Automation) tools.",
)

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

Use the unified `MCPToolset("http://...")` setup. Pass it into your agent via the `toolsets=[toolset]` parameter. The older HTTP server classes are deprecated.

The framework fails loudly. If `list_scenario_logs` returns data that doesn't match your Pydantic model, it throws a validation error. It never lets the agent guess the contents.

Yes. The framework is entirely model-agnostic. As long as the local model supports tool calling, it can interact with `get_scenario` and other endpoints.

It executes `list_organizations` first to retrieve the authenticated user's details. It then uses that validated ID to query specific scenarios. Every step is type-checked at runtime.

No. The server reads connection metadata via `list_connections` but never exposes the underlying OAuth tokens. Your Pydantic models only receive the safe, structured metadata required for auditing.

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