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

Q: How do I handle the initial Postgres sync using ElectricSQL (Sync Engine) in LangChain?

Call the getshape tool with offset=-1 to fetch the complete initial state of your target table. Your LangChain agent can then process this raw array of Postgres records as a clean document list.

Q: Can I track ElectricSQL (Sync Engine) tool calls inside LangChain?

Yes, every execution of getshape or postshape shows up automatically in LangSmith. You can monitor the exact JSON payload returned from your Postgres database and see how it affects your agent's reasoning.

Q: How do I set up the ElectricSQL (Sync Engine) MCP server with LangChain?

Install langchain-mcp-adapters and use the MultiServerMCPClient pointing to your Vinkius endpoint. From there, extract the tools and pass them directly to your agent constructor.

Get real-time Postgres tables streamed directly into your LangChain decision loops with this lightweight 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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Postgres shapes directly into LangChain chains

The `get_shape` tool pulls targeted slices of Postgres data directly into your LangChain runnables. By specifying an offset of -1, your chain fetches a clean snapshot of your database table without writing custom SQL queries or managing complex connection pools. This setup allows your ReAct agents to inspect the actual state of your database before deciding on the next tool execution. You can inspect exactly how the data flows through your chains using LangSmith, tracking latency and token usage for every single Postgres sync event.

Post custom Postgres shapes in LangChain pipelines

The `post_shape` tool lets your agent define and request specific subsets of Postgres tables on the fly. Instead of pulling massive, unfiltered datasets, your chain posts a precise shape definition to isolate only the records it needs for the current task. Your LangChain agent can use the output of a previous retrieval step to construct this POST request. By linking these steps, you prevent the agent from hallucinating on stale database records and keep token costs down.

Aggregate the MCP Server with other LangChain tools

Both `get_shape` and `post_shape` work within an MCP server configuration to combine Postgres data with other external APIs. You can instantiate this server alongside vector databases or messaging tools to build a single, unified toolset for your agent. This means your chains can pull a Postgres shape, process it, and immediately send it to another service. You get a stateless, composable setup where live database sync is just one tool in a larger, multi-step pipeline.

Setup guide

Set up ElectricSQL (Sync Engine) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ElectricSQL (Sync Engine) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "electricsql-sync-engine-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ElectricSQL (Sync Engine) transactions"
    })
    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 LangChain

Call the `get_shape` tool with `offset=-1` to fetch the complete initial state of your target table. Your LangChain agent can then process this raw array of Postgres records as a clean document list.

Yes, every execution of `get_shape` or `post_shape` shows up automatically in LangSmith. You can monitor the exact JSON payload returned from your Postgres database and see how it affects your agent's reasoning.

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` pointing to your Vinkius endpoint. From there, extract the tools and pass them directly to your agent constructor.

The server handles all HTTP connections to the sync engine under the hood. Your LangChain runnables make simple, stateless tool calls without maintaining persistent TCP sockets to Postgres.

Your Postgres database records are isolated within Vinkius's secure sandboxed isolates. No data is stored on disk, and the ephemeral execution environment ensures that your sync shapes are never cached or exposed to third parties.

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