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

Q: How do I register ElectricSQL (Sync Engine) tools in LlamaIndex using this MCP server?

Use the llama-index-tools-mcp package to connect to the Vinkius URL. Then, wrap the client in McpToolSpec and convert it to a tool list for your agent.

Q: Can LlamaIndex index live updates from ElectricSQL (Sync Engine)?

Yes, by calling getshape periodically or on-demand, LlamaIndex pulls the latest Postgres updates. You can then parse these shapes into nodes and update your vector store index.

Q: What is the best way to handle initial Postgres syncs in LlamaIndex with ElectricSQL (Sync Engine)?

Trigger getshape with offset=-1 to fetch the initial snapshot of your Postgres data. This ensures your LlamaIndex knowledge base starts with a complete dataset before processing incremental updates.

Index live Postgres shapes directly into your LlamaIndex vector stores 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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extract Postgres shapes into LlamaIndex documents

The `get_shape` tool retrieves specific Postgres table schemas and data slices as raw JSON inputs for your indexers. Passing an offset of -1 triggers an initial sync, giving your pipeline a clean baseline of your database state. LlamaIndex converts these Postgres shapes into document nodes that you can immediately ingest into vector databases. This keeps your semantic search index constantly updated with fresh records instead of relying on stale manual exports.

Post Postgres shapes from LlamaIndex agents

The `post_shape` tool enables your LlamaIndex agents to request customized data subsets from Postgres using POST requests. The agent determines what data subset is relevant to the user query and registers that shape dynamically. This allows your RAG application to avoid fetching irrelevant database rows. By indexing only the returned shape, you reduce search noise and ensure the agent synthesizes answers from highly relevant, real-time database contexts.

Build a queryable index of your MCP Server data

Both `get_shape` and `post_shape` outputs can be piped into a `FunctionAgent` to create a live, queryable knowledge base using this MCP server. The LlamaIndex agent calls these tools to check current database values before generating a response. This setup guarantees that your RAG pipeline is grounded in actual Postgres tables. You don't have to write custom ETL pipelines because the sync engine provides the data directly to the agent's tool spec.

Setup guide

Set up ElectricSQL (Sync Engine) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all ElectricSQL (Sync Engine) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to ElectricSQL (Sync Engine) tools.",
)
response = await agent.run("List recent ElectricSQL (Sync Engine) data")

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 LlamaIndex

Use the `llama-index-tools-mcp` package to connect to the Vinkius URL. Then, wrap the client in `McpToolSpec` and convert it to a tool list for your agent.

Yes, by calling `get_shape` periodically or on-demand, LlamaIndex pulls the latest Postgres updates. You can then parse these shapes into nodes and update your vector store index.

Trigger `get_shape` with `offset=-1` to fetch the initial snapshot of your Postgres data. This ensures your LlamaIndex knowledge base starts with a complete dataset before processing incremental updates.

The tool spec loads the shape data into memory as a list of documents. If you expect massive tables, use `post_shape` to define smaller, highly filtered subsets.

Your Postgres database records pass through a zero-trust, ephemeral V8 sandbox on Vinkius. The data is streamed directly to your LlamaIndex client over HTTPS, ensuring your database credentials and shapes are never stored.

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