How to Use the MyScale (SQL Vector Database API) MCP in LlamaIndex

Q: How do I index query results from MyScale (SQL Vector Database API) using LlamaIndex?

You run executesqlquery through your agent to retrieve the raw rows. LlamaIndex then takes those returned documents, packages them into node objects, and inserts them into your local index for semantic retrieval.

Q: Can LlamaIndex automatically build vector indices in MyScale (SQL Vector Database API) using an MCP Server?

Yes, your agent can call createvectortable to establish the schema and then run createvectorindex. It can track the building process with checkindexstatus before starting any RAG operations.

Q: How does LlamaIndex handle connection timeouts with MyScale (SQL Vector Database API)?

The agent can run pingcluster as an initial sanity check. If the database does not respond within your specified timeout window, LlamaIndex can route the query to an alternative data source.

Q: Can I run custom SQL joins along with vector searches?

Yes, you can use executesqlquery to write complex SQL statements that join vector tables with standard relational tables. This allows you to filter search results using structured metadata before returning them to your agent.

Feed live SQL vector search results from MyScale (SQL Vector Database API) directly into your LlamaIndex knowledge graphs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MyScale (SQL Vector Database API) MCP to LlamaIndex

Create your Vinkius account to connect MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live MyScale MCP Server Data into LlamaIndex

Your LlamaIndex agent runs `vector_search` to pull raw database matches and immediately indexes them into a local document store. This lets you combine structured SQL tables with unstructured knowledge bases in real time. Instead of running batch syncs, your agent executes queries dynamically using `execute_sql_query` and updates its search index on the fly. Your pipeline is guaranteed to operate on the most current data available in your database.

Automated Schema Setup and Search Indexing

Let your LlamaIndex agent prepare its own storage environments by calling `create_vector_table` directly. By calling `create_vector_table` through this MCP server, the agent builds tables matching your specific data schemas without requiring manual database migration scripts. Once the tables are populated, the agent fires `create_vector_index` to optimize search performance. It then monitors the setup progress via `check_index_status` to ensure your search queries run with minimal latency.

Verify Cluster Availability Before Querying

Avoid application crashes by letting your agent verify database status with `ping_cluster` before executing heavy retrieval tasks. The agent uses `ping_cluster` via the MCP server to check connection health before pulling documents for context generation. If the connection is healthy, LlamaIndex routes the user query to `vector_search` to fetch the most relevant context. Offline clusters trigger the agent to gracefully fall back to local document stores or cached results.

Setup guide

Set up MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) tools.",
)
response = await agent.run("List recent MyScale (SQL Vector Database API) 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 MyScale. 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) MCP in LlamaIndex

You run `execute_sql_query` through your agent to retrieve the raw rows. LlamaIndex then takes those returned documents, packages them into node objects, and inserts them into your local index for semantic retrieval.

Yes, your agent can call `create_vector_table` to establish the schema and then run `create_vector_index`. It can track the building process with `check_index_status` before starting any RAG operations.

The agent can run `ping_cluster` as an initial sanity check. If the database does not respond within your specified timeout window, LlamaIndex can route the query to an alternative data source.

Yes, you can use `execute_sql_query` to write complex SQL statements that join vector tables with standard relational tables. This allows you to filter search results using structured metadata before returning them to your agent.

Vinkius executes this MCP server within an ephemeral, zero-trust container. Your SQL queries and raw vector embeddings are processed locally, meaning no database records or structural metadata are ever stored on external logging servers.

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