How to Use the Amazon DynamoDB Table MCP in LlamaIndex

Q: How do I load the Amazon DynamoDB Table MCP Server into LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient. Wrap it in McpToolSpec to expose tools like getitem and querytable to your LlamaIndex FunctionAgent.

Q: Can LlamaIndex query an Amazon DynamoDB Table without scanning the whole thing?

Yes, your LlamaIndex agent can use querytable to target specific partition keys. This is much faster and cheaper than running scantable over your entire dataset.

Q: Does LlamaIndex support writing data back to the Amazon DynamoDB Table?

Yes, your agent can write new records using putitem and remove old ones using deleteitem. This lets your index pipeline modify database records during its execution run.

Index live Amazon DynamoDB Table records directly into LlamaIndex vector stores for hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon DynamoDB Table MCP to LlamaIndex

Create your Vinkius account to connect Amazon DynamoDB Table 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 DynamoDB Table with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing live database records for LlamaIndex RAG

Instead of working with static documents, this MCP server allows LlamaIndex to pull live data directly from your database using `scan_table`. Your indexer runs the scan tool to ingest the latest records and convert them into searchable vector embeddings. This setup ensures your search indexes are always grounded in real-time application data. Your query engine can retrieve the most up-to-date database records instead of relying on stale text files.

Hybrid search combining vector and NoSQL queries

Let your LlamaIndex agent decide when to search semantic embeddings and when to fetch exact records using `get_item`. The agent can use the tool to grab a specific user profile by its ID while using vector search to find related documents via the MCP protocol. If the semantic search needs structured metadata, the agent runs `query_table` to filter results based on specific database attributes. This hybrid approach gives you the precision of a NoSQL database alongside the flexibility of vector search.

Automated database updates from agent runs

Keep your knowledge base updated by letting your agent write directly to the table during execution using `put_item` via our hosted MCP infrastructure. When LlamaIndex processes new information, it can run the tool to store the structured output directly in your database. The agent can also clean up outdated or redundant entries using `delete_item` based on feedback loops. This turns your static data index into an active, self-cleaning knowledge system.

Setup guide

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

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient`. Wrap it in `McpToolSpec` to expose tools like `get_item` and `query_table` to your LlamaIndex `FunctionAgent`.

Yes, your LlamaIndex agent can use `query_table` to target specific partition keys. This is much faster and cheaper than running `scan_table` over your entire dataset.

Yes, your agent can write new records using `put_item` and remove old ones using `delete_item`. This lets your index pipeline modify database records during its execution run.

You configure your AWS credentials once on our platform. The server handles the handshake securely, so your LlamaIndex application only needs a single endpoint token to run database operations.

Your database records are transmitted through encrypted channels directly to your LlamaIndex client. We run the translation layer in ephemeral, isolated sandboxes, ensuring your raw NoSQL data is never stored or logged on our 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