How to Use the Iterable MCP in Pydantic AI

Q: How do I import the Iterable MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and use the MCPToolset constructor pointing to your Vinkius HTTP endpoint. Pass the toolset directly to your Agent via the toolsets list.

Q: Why should I use Pydantic AI for querying Iterable campaign metrics?

Calling getcampaignmetrics returns complex numeric data that Pydantic AI validates against strict Python types. This guarantees your agent never processes malformed click rates or invalid conversion counts.

Q: Does this MCP Server support SSE transports in Pydantic AI?

Yes, MCPToolset supports both Streamable HTTP and SSE transports, allowing you to connect to your externally hosted Vinkius server directly.

Q: Is the legacy MCPServerHTTP class still used for Iterable integrations in Pydantic AI?

No, you should use the unified MCPToolset class. The old MCPServerHTTP class is deprecated and may cause issues in newer versions of the framework.

Q: How does Vinkius protect the privacy of my Iterable templates and workflows?

Vinkius uses ephemeral V8 sandboxes to isolate every listtemplates and listworkflows call. Your template content and marketing logic are processed in memory and immediately discarded.

Run type-safe Iterable campaign lookups and user audits using Pydantic AI 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 Iterable MCP to Pydantic AI

Create your Vinkius account to connect Iterable 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 Iterable with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate subscriber profiles at runtime with Pydantic AI

`get_user` fetches subscriber profiles by email and validates the returning JSON payload against your Pydantic schemas. If the API returns unexpected custom fields or missing data types, the framework raises a validation error immediately. This prevents corrupted user profiles from breaking your downstream application logic. Your agent uses this validated data to check list memberships via `list_lists`. Because the schemas are strictly typed, your Pydantic agent can write assertions about segment membership without risking silent runtime failures.

Verify template structures using this MCP Server

`list_templates` pulls the available message templates in your account, including metadata and unique identifiers. Your agent reads these templates to verify which layouts are ready for deployment. The agent maps these templates to active outreach campaigns by cross-referencing them with `list_campaigns`. This ensures your Pydantic AI agent only schedules campaigns that have valid, existing templates assigned to them.

Monitor automation health with Pydantic AI

`list_workflows` returns all automated marketing sequences and trigger rules. Your agent parses this structured list to map out active customer journeys. It then verifies how these workflows classify communications by calling `list_message_types`. This strict validation ensures that automated triggers always map to the correct regulatory message classifications.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and use the `MCPToolset` constructor pointing to your Vinkius HTTP endpoint. Pass the toolset directly to your `Agent` via the `toolsets` list.

Calling `get_campaign_metrics` returns complex numeric data that Pydantic AI validates against strict Python types. This guarantees your agent never processes malformed click rates or invalid conversion counts.

Yes, `MCPToolset` supports both Streamable HTTP and SSE transports, allowing you to connect to your externally hosted Vinkius server directly.

No, you should use the unified `MCPToolset` class. The old `MCPServerHTTP` class is deprecated and may cause issues in newer versions of the framework.

Vinkius uses ephemeral V8 sandboxes to isolate every `list_templates` and `list_workflows` call. Your template content and marketing logic are processed in memory and immediately discarded.

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