How to Use the ElectricSQL (Sync Engine) MCP in Pydantic AI

Type-safe Postgres synchronization for Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ElectricSQL (Sync Engine) MCP to Pydantic AI

Create your Vinkius account to connect ElectricSQL (Sync Engine) 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 ElectricSQL (Sync Engine) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-validated Postgres sync for Pydantic AI

The `get_shape` tool brings Postgres data into your agent with strict schema adherence. Because you use Pydantic AI, any unexpected data format triggers a validation error instantly. This prevents your agent from acting on corrupted or malformed data. You get a guarantee that the context the agent receives matches your defined model requirements.

Shape definition with Pydantic AI

The `post_shape` tool allows your agent to request data subsets that align with your Pydantic models. It simplifies the bridge between your database and your typed agent logic. This approach removes the guesswork from your data ingestion. Your agent knows exactly what to expect from every tool call, which keeps your code clean and predictable.

Unified MCP Server transport

Configure the MCPToolset to handle your HTTP connections. It integrates cleanly into your agent's toolset array, providing a standard way to interact with the sync engine. You avoid the overhead of deprecated connection methods. It is a straightforward setup that lets you focus on building robust agents without worrying about the underlying sync transport.

Setup guide

Set up ElectricSQL (Sync Engine) 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": {
        "electricsql-sync-engine-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent ElectricSQL (Sync Engine) 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 ElectricSQL. 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 ElectricSQL (Sync Engine) 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 ElectricSQL (Sync Engine) MCP in Pydantic AI

It provides a type-safe way to sync Postgres. Pydantic AI validates every response, ensuring your agent only works with data that matches your models.

The framework will throw a validation error if the sync engine returns fields that don't match your Pydantic models. This stops bad data before it reaches your agent's reasoning loop.

It doesn't dictate your models. You define the Pydantic classes, and the MCP Server delivers the data that you then validate against those classes.

The server only exposes the shapes you explicitly define. It acts as a gatekeeper for your Postgres data, ensuring only permitted subsets reach your agent.

Yes, you can pass an array of toolsets to your agent. This server will run alongside others, each providing its own set of validated tools.

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