How to Use the Amazon Redshift MCP in LlamaIndex

Q: How can LlamaIndex query Amazon Redshift and use the results?

Your LlamaIndex agent calls executesql, polls statementstatus until completion, and then uses getresults. The returned data can then be passed directly into a LlamaIndex data structure to be chunked and indexed for RAG.

Q: Can LlamaIndex create a knowledge base of my Amazon Redshift schema?

Absolutely. You can have your agent run listschemas and listtables to get a complete map of your database. You then index this output, creating a searchable document that describes your data warehouse structure.

Ground your LlamaIndex RAG apps in live data by indexing query results from Amazon Redshift.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Redshift MCP to LlamaIndex

Create your Vinkius account to connect Amazon Redshift 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 Amazon Redshift with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Source Live Data for Your Index

Turn your Redshift warehouse into a queryable knowledge source. Your agent uses `execute_sql` to run a query and, after checking `statement_status`, pulls the data with `get_results`. LlamaIndex can then take this structured data—fresh from your warehouse—and automatically ingest it into a vector index. This means your RAG application's answers are always based on the most current information, not a stale copy.

Enrich Your Index with Schema Metadata

A good knowledge base needs context. Use the `list_schemas`, `list_tables`, and `describe_table` tools to pull structural information about your database. You can index this metadata alongside your query results. When a user asks "What columns are in the users table?", your LlamaIndex agent can answer instantly by retrieving the indexed output of a `describe_table` call.

Build a Searchable Query History with this MCP Server

Keep a record of what's been asked and run. The `list_statements` tool retrieves a history of executed SQL. Your agent can call this periodically and add the results to your LlamaIndex knowledge base. This creates a searchable audit log. You can ask your RAG agent questions like "What were the five most recent failed queries?" and get an answer grounded in the actual data from your MCP server.

Setup guide

Set up Amazon Redshift 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 Amazon Redshift 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 Amazon Redshift tools.",
)
response = await agent.run("List recent Amazon Redshift 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 Amazon Redshift. 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 Amazon Redshift 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 Amazon Redshift MCP in LlamaIndex

Your LlamaIndex agent calls `execute_sql`, polls `statement_status` until completion, and then uses `get_results`. The returned data can then be passed directly into a LlamaIndex data structure to be chunked and indexed for RAG.

Absolutely. You can have your agent run `list_schemas` and `list_tables` to get a complete map of your database. You then index this output, creating a searchable document that describes your data warehouse structure.

The asynchronous design is perfect for this. Your agent fires the query with `execute_sql` and can perform other tasks while it runs. It only calls `get_results` after `statement_status` confirms the query is finished, so your agent doesn't get stuck waiting.

This MCP server gives you a managed, secure layer. You don't package database drivers or handle credentials. Vinkius provides a single, secured endpoint that's ready to plug into your LlamaIndex `McpToolSpec`.

This server processes the SQL statements you send, plus the schema metadata and query results you retrieve. Your connection is secured by a single Vinkius token, not raw database credentials. Every tool call runs in a dedicated, zero-trust sandbox that is torn down immediately after.

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