How to Use the Vald MCP in LlamaIndex

Q: If I modify a record, how do I ensure LlamaIndex sees it?

You must call updatevector, supplying both the original ID and the complete new vector array. This ensures the index is updated correctly before running a subsequent query.

Q: What happens if I delete data from Vald for LlamaIndex?

Calling deletevector is irreversible. It removes the vector permanently, meaning that knowledge can no longer be retrieved or indexed by your LlamaIndex application.

Q: If I need to check system status with Vald and LlamaIndex?

Use getengineinfo. This tool provides operational information about the entire MCP Server, letting you confirm that Vald is running optimally for your knowledge-augmented application.

Build searchable knowledge bases with Vald and LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vald MCP to LlamaIndex

Create your Vinkius account to connect Vald 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 Vald with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Augment RAG Pipelines with Vald

LlamaIndex uses `search_vectors` to find relevant context for your application. You provide a query vector, and the tool returns the nearest neighbors from the stored index. This output grounds your LLM responses in verifiable API data. The result of this MCP Server call becomes part of the searchable knowledge base, making live operational data available for semantic retrieval.

Maintain a Detailed History using Vald

Use `get_vector_details` to pull raw vector information by ID. This is crucial when building applications that need to query past sessions or configurations stored in the index. If you modify a record, remember to use `update_vector`. Supply both the existing ID and the full new vector array so LlamaIndex can accurately map the change.

Monitor Vald MCP Server Health

Before running complex queries, check the system with `get_engine_info`. This tool provides operational details about the entire database engine. It's good practice to run this first. Need to add a new knowledge source? Use `insert_vector` by providing a unique ID and the vector array. This immediately makes the data queryable in your LlamaIndex application.

Setup guide

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

Vald provides structured, searchable vectors. Instead of just passing documents, LlamaIndex can query the MCP Server to get answers grounded in actual API data using tools like `search_vectors`.

You must call `update_vector`, supplying both the original ID and the complete new vector array. This ensures the index is updated correctly before running a subsequent query.

Yes. The MCP Server is designed as a highly scalable, distributed nearest-neighbor engine. You manage this scale by using `insert_vector` to add new vectors and then querying them.

Calling `delete_vector` is irreversible. It removes the vector permanently, meaning that knowledge can no longer be retrieved or indexed by your LlamaIndex application.

Use `get_engine_info`. This tool provides operational information about the entire MCP Server, letting you confirm that Vald is running optimally for your knowledge-augmented application.

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