How to Use the DataStax Astra DB Vector MCP in LlamaIndex

Q: How do I connect DataStax Astra DB Vector to LlamaIndex?

Run pip install llama-index-tools-mcp. Set up a BasicMCPClient for your MCP Server using your Vinkius URL, wrap it in an McpToolSpec, and pass the generated tools to your FunctionAgent.

Q: Can LlamaIndex query NoSQL documents from DataStax Astra DB Vector?

Yes. The agent executes finddocuments to pull standard JSON records. It then synthesizes those records into grounded answers for your users.

Q: Does DataStax Astra DB Vector support ANN queries in LlamaIndex?

The integration includes a dedicated vectorsearch tool. Your agent uses it to find semantically similar documents based on the user's prompt.

Ground your LlamaIndex RAG applications with live NoSQL data and vector similarity matching from DataStax Astra DB Vector.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DataStax Astra DB Vector MCP to LlamaIndex

Create your Vinkius account to connect DataStax Astra DB Vector 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 DataStax Astra DB Vector with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounded RAG via MCP Server

LlamaIndex thrives on contextual data. By connecting this MCP Server, your `FunctionAgent` executes `vector_search` to pull ANN similarity results directly from your Astra DB collections. The agent treats live database queries as just another source of truth. Instead of relying on static files, your query engine accesses real-time NoSQL records. Calling `find_documents` or `find_one_document` retrieves specific metadata that gets synthesized into the final response. You get answers based on actual database state.

Dynamic Indexing and Insertion

RAG applications often generate new insights that belong in the knowledge base. Your agent formats these findings and uses `insert_document` to push them back into Astra DB. This includes attaching a pre-generated `$vector` key for future retrieval. Keeping track of where that data lives is straightforward. The `list_collections` tool allows the agent to map out the current namespace before deciding where to store or query information. Everything stays organized within your LlamaIndex architecture.

Index Maintenance

Stale data ruins RAG accuracy. When an agent determines a source is outdated, it triggers `delete_document` to remove the offending record from the Astra collection. Measuring the size of your current knowledge base happens instantly. The agent runs `count_documents` to verify insertion success or check collection volume. Your application maintains a precise understanding of its available context.

Setup guide

Set up DataStax Astra DB Vector 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 DataStax Astra DB Vector 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 DataStax Astra DB Vector tools.",
)
response = await agent.run("List recent DataStax Astra DB Vector 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 DataStax Astra DB. 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 DataStax Astra DB Vector 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 DataStax Astra DB Vector MCP in LlamaIndex

Run `pip install llama-index-tools-mcp`. Set up a `BasicMCPClient` for your MCP Server using your Vinkius URL, wrap it in an `McpToolSpec`, and pass the generated tools to your `FunctionAgent`.

Yes. The agent executes `find_documents` to pull standard JSON records. It then synthesizes those records into grounded answers for your users.

The integration includes a dedicated `vector_search` tool. Your agent uses it to find semantically similar documents based on the user's prompt.

Vinkius handles all the underlying authentication securely. You only provide the platform's endpoint token to establish the MCP connection.

Every request processes inside an isolated, zero-trust V8 environment. Vinkius never logs or retains the NoSQL documents, `$vector` keys, or collection schemas returned by your queries.

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