How to Use the ElectricSQL (Sync Engine) MCP in AutoGen

Q: How do I add ElectricSQL (Sync Engine) tools to an AutoGen agent using this MCP server?

Install autogen-extmcp and use the mcpservertools helper with your Vinkius endpoint. Pass the resulting tool list directly to your AssistantAgent configuration.

Q: How do AutoGen agents handle the initial Postgres sync with ElectricSQL (Sync Engine)?

The executing agent calls getshape with offset=-1 to retrieve the initial dataset. The agent then prints or formats this Postgres snapshot so the rest of the group can read it.

Let your AutoGen agents debate and coordinate real-time Postgres syncs using this MCP Server.

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 AutoGen

Create your Vinkius account to connect ElectricSQL (Sync Engine) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Postgres shape gets within AutoGen debates

The `get_shape` tool allows your AutoGen database agent to fetch specific Postgres tables with an offset of -1 for a complete initial sync. Once fetched, the data is shared in the conversation thread where other agents can analyze it. This allows a data analyst agent to pull records while a supervisor agent checks the schema for anomalies. The entire process happens asynchronously within the conversation loop without manual developer intervention.

Post Postgres shapes through AutoGen agent consensus

The `post_shape` tool lets your AutoGen agents collaboratively define and post new data shapes to Postgres. A planning agent can propose a specific database query, and a security agent can validate the shape before the tool executes. By using POST requests to register these subsets, your agents only sync the precise data needed for their current task. This prevents performance bottlenecks and keeps the conversational context window clean.

Convert this MCP Server tools for AutoGen agents

Both `get_shape` and `post_shape` tools are automatically converted to AutoGen-compatible schemas using the `McpToolAdapter` on this MCP server. You pass the tools directly to your `AssistantAgent` constructor without writing any custom glue code. This integration supports both stdio and streamable HTTP transports. Your multi-agent system can instantly start querying Postgres tables, making consensus-driven decisions based on real-time database state.

Setup guide

Set up ElectricSQL (Sync Engine) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes ElectricSQL (Sync Engine) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="ElectricSQL (Sync Engine)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ElectricSQL (Sync Engine) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="ElectricSQL (Sync Engine)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ElectricSQL (Sync Engine) data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` and use the `mcp_server_tools` helper with your Vinkius endpoint. Pass the resulting tool list directly to your `AssistantAgent` configuration.

Yes, the server handles concurrent requests, allowing different agents to call `get_shape` or `post_shape` as they debate. The outputs are shared across the conversation context.

The executing agent calls `get_shape` with `offset=-1` to retrieve the initial dataset. The agent then prints or formats this Postgres snapshot so the rest of the group can read it.

If a shape request fails, the server returns the raw HTTP error. Your AutoGen agents can read this error, adjust their shape definition, and try the tool call again.

Yes, your Postgres database records are protected by end-to-end TLS encryption and ephemeral execution environments. Vinkius runs the server in a secure, isolated sandbox, meaning your shapes are never persisted or exposed.

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