How to Use the Hightouch (Reverse ETL) MCP in Pydantic AI

Q: How do I instantiate the Hightouch (Reverse ETL) toolset in Pydantic AI?

Use the unified MCPToolset constructor passing your Vinkius HTTP endpoint. Do not use the deprecated MCPServerHTTP class; the new toolset approach is the standard for modern integrations.

Build type-safe Pydantic AI agents that monitor Hightouch syncs via MCP with strict, runtime-validated schema enforcement.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hightouch (Reverse ETL) MCP to Pydantic AI

Create your Vinkius account to connect Hightouch (Reverse ETL) 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 Hightouch (Reverse ETL) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe pipeline monitoring with Pydantic AI

Your agent validates pipeline states at runtime by pulling data from `list_syncs` and `get_sync`. This MCP Server integration forces every payload through strict runtime validation before your agent ever sees it. If the Hightouch API structure changes or returns unexpected null values, your Pydantic AI agent fails immediately. This prevents your Pydantic AI decision-making loops from acting on corrupted or incomplete Hightouch pipeline states.

Validate data models before they fail

Your Pydantic AI agent catches schema drift by calling `list_models` to inspect active SQL definitions. It validates these definitions against your local database configurations to catch Hightouch mismatches early. By comparing these models with the outputs of `list_sources`, the Pydantic AI agent flags mismatched fields or missing columns. You get a reliable early-warning system for your data pipeline that runs entirely on structured Pydantic AI Python objects.

Track operational history without silent failures

Parse historical Hightouch performance data with absolute confidence using Pydantic AI and MCP tools. The Pydantic AI agent calls `list_sync_runs` to inspect execution times, row counts, and error messages. Because every field is strictly typed, your Pydantic AI agent can safely calculate average execution speeds and failure rates. It then cross-references these with `list_destinations` to isolate flaky Hightouch API targets.

Setup guide

Set up Hightouch (Reverse ETL) 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": {
        "hightouch-reverse-etl-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Hightouch (Reverse ETL) 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 Hightouch. 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 Hightouch (Reverse ETL) 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 Hightouch (Reverse ETL) MCP in Pydantic AI

Use the unified `MCPToolset` constructor passing your Vinkius HTTP endpoint. Do not use the deprecated `MCPServerHTTP` class; the new toolset approach is the standard for modern integrations.

Pydantic AI throws a validation error at runtime. This guarantees your agent never attempts to parse malformed run histories or corrupted destination lists.

Yes, you can connect using either transport method via the toolset. Make sure your external server is running and accessible before initializing the toolset in your agent code.

Yes, Pydantic AI is completely model-agnostic. You can run the agent with local models or alternative cloud APIs while maintaining strict type-safety across all Hightouch tools.

All connections run through a zero-trust, ephemeral V8 isolate sandbox on Vinkius. The MCP Server only handles structural metadata like source types and sync schedules, keeping your raw customer data completely isolated.

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