How to Use the Flodesk MCP in Pydantic AI

Q: How do I register the Flodesk MCP Server in Pydantic AI?

Instantiate the MCPToolset with the Vinkius server URL and pass it into the Agent constructor. This automatically registers all ten MCP tools for runtime validation.

Q: How do I fetch a list of active workflows?

Your agent calls listworkflows to get a structured list of sequences. The response is parsed into validated objects so your agent knows exactly which IDs are valid.

Build type-safe Pydantic AI agents that manage Flodesk subscribers and segments with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flodesk MCP to Pydantic AI

Create your Vinkius account to connect Flodesk 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 Flodesk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe subscriber updates with Pydantic AI validation

This MCP Server exposes `upsert_subscriber` and `get_subscriber` to your Pydantic AI workflows with strict runtime validation of Flodesk profiles. If the Flodesk API returns unexpected fields, the Pydantic AI framework catches the discrepancy immediately. It crashes early. This guarantees that your Pydantic AI agent never writes malformed data to your Flodesk subscriber lists. You avoid silent data corruption because any schema deviation triggers a loud validation error before the Flodesk database is touched.

Rigid segment management without silent failures

The `create_segment` and `add_subscriber_to_segment` tools let you organize your Flodesk audience with total structural confidence using Pydantic AI. Pydantic AI validates the Flodesk segment payload against your defined models before dispatching the request. No silent failures. If your Pydantic AI agent attempts to add a subscriber to a non-existent Flodesk segment, the system halts execution. This strictness keeps your Flodesk list hygiene pristine and prevents broken automation triggers.

Verify workflow triggers and custom field schemas

The `list_custom_fields` and `list_workflows` tools allow your Pydantic AI agent to inspect your Flodesk setup before acting. Pydantic AI parses these Flodesk lists into typed objects, ensuring your agent reads the exact metadata fields available. When triggering a sequence via `add_subscriber_to_workflow` in Pydantic AI, the framework validates that the Flodesk subscriber exists and matches the required criteria. You get clean, predictable Flodesk execution across OpenAI, Anthropic, or local models.

Setup guide

Set up Flodesk 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": {
        "flodesk-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Instantiate the `MCPToolset` with the Vinkius server URL and pass it into the Agent constructor. This automatically registers all ten MCP tools for runtime validation.

The framework raises a validation error immediately. This prevents your agent from processing corrupted subscriber data or making assumptions about missing fields.

Yes, you can define a Pydantic model for your custom fields. The agent validates the data against this model before invoking `upsert_subscriber`.

Your agent calls `list_workflows` to get a structured list of sequences. The response is parsed into validated objects so your agent knows exactly which IDs are valid.

Data processing occurs entirely in memory within your local runtime environment. Vinkius provides token-based authentication and ephemeral MCP execution paths, ensuring subscriber emails are never logged or stored.

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