How to Use the Vectara MCP in LlamaIndex

Q: How do I check corpus configuration using Vectara with LlamaIndex?

Call getcorpusdetails. This tool retrieves the specific metadata and setup details for a given corpus. It helps ensure that the data source is properly configured before indexing.

Q: What if I need to delete documents using Vectara with LlamaIndex?

Use deletecorpusdocument to permanently remove an indexed document from a corpus. This action removes it from the searchable knowledge base; double-check your parameters first.

Q: Can I search across multiple datasets using Vectara with LlamaIndex?

Yes, performsemanticsearch lets you specify one or more corpus keys. This capability is critical when building a unified index from disparate data sources.

Q: How do I list all available datasets using Vectara with LlamaIndex?

The developer uses the listcorpora tool to get an inventory of every dataset. This step is necessary for initializing the source resources for the RAG application.

Build knowledge-augmented RAG apps with LlamaIndex using Vectara's indexed data tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vectara MCP to LlamaIndex

Create your Vinkius account to connect Vectara 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 Vectara with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and chat using live documents

The `execute_rag_chat` tool runs a chat completion that grounds the AI response in your corpus, providing citations for every claim. LlamaIndex can use this output to update its knowledge base, making it more searchable. You don't just read; you query. Use `perform_semantic_search` when you need to find specific concepts across one or multiple corpora before building a definitive answer.

Index and manage all datasets

To build your RAG application, you first need to know what's available. `list_corpora` shows every dataset in the Vectara account, while `get_corpus_details` pulls metadata for a single corpus. You can also list exactly which documents are inside a specific corpus using `list_corpus_documents`. This gives LlamaIndex visibility into the raw data sources.

Cleanup and maintenance of corpora

Sometimes you need to retire old data. The `delete_corpus_document` tool permanently removes a document from a corpus, ensuring clean data for your index. Be careful running this—it’s irreversible. LlamaIndex can integrate this cleanup step into its pipeline, allowing the developer to manage data decay and maintain high-quality search results.

Setup guide

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

Call `get_corpus_details`. This tool retrieves the specific metadata and setup details for a given corpus. It helps ensure that the data source is properly configured before indexing.

Use `delete_corpus_document` to permanently remove an indexed document from a corpus. This action removes it from the searchable knowledge base; double-check your parameters first.

Yes, `perform_semantic_search` lets you specify one or more corpus keys. This capability is critical when building a unified index from disparate data sources.

The developer uses the `list_corpora` tool to get an inventory of every dataset. This step is necessary for initializing the source resources for the RAG application.

This server touches Corpus Metadata, which includes system-level information about your datasets. The `list_corpora` tool confirms the structure of these metadata objects.

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