How to Use the Vectara MCP in Mastra AI

Q: How do I monitor data changes in Vectara using Mastra AI?

You use listcorpusdocuments to get a current list of all indexed files within a corpus. This is vital for building workflows that must react to dataset updates.

Q: Can I see the configuration details of a specific data source with Vectara and Mastra AI?

Yes, call getcorpusdetails and pass in the corpus key. This returns all necessary metadata about that particular dataset for your workflow engine to consume.

Q: What is the process for deleting documents from Vectara using Mastra AI?

The deletecorpusdocument action permanently removes a document. Since this is irreversible, ensure your multi-step workflow has proper confirmation checks before executing this tool.

Q: If I need to verify available search indexes in Vectara using Mastra AI?

You first run listcorpora to get all names. Then you can target those specific keys with performsemanticsearch to test the scope of your data.

Build resilient, multi-step workflows with Mastra AI and MCP Server 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 Mastra AI

Create your Vinkius account to connect Vectara to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated RAG Chat via MCP Server

You can execute a fully grounded chat completion using `execute_rag_chat`. Just provide the corpus keys and the user's query, and you get an AI summary with citations attached. It’s reliable. This ability is great for building automated processes that need to answer questions based on specific, controlled knowledge bases without human input.

Workflow Tooling: Corpus Management

Mastra AI needs to manage data scope. Use `list_corpora` and `get_corpus_details` to understand the structure of your available datasets. This gives you control over which knowledge bases are included in a complex workflow step. Furthermore, if a workflow fails because it's pointing at an outdated dataset, you can use these tools to check the metadata and get the system back on track.

Error Handling with Semantic Search

When building complex workflows, failure is expected. `perform_semantic_search` helps by providing a mechanism to gather contextual data even if a primary API call fails. You pass the corpus keys and query text to get immediate results. This allows your agent to perform smart failovers—if one tool breaks, it can fall back to searching for related information instead.

Setup guide

Set up Vectara MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Vectara tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "vectara-mcp-client",
  servers: {
    "vectara-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Vectara Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Vectara tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Vectara transactions"
);
console.log(result.text);

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 Mastra AI

You use `list_corpus_documents` to get a current list of all indexed files within a corpus. This is vital for building workflows that must react to dataset updates.

Yes, call `get_corpus_details` and pass in the corpus key. This returns all necessary metadata about that particular dataset for your workflow engine to consume.

The `delete_corpus_document` action permanently removes a document. Since this is irreversible, ensure your multi-step workflow has proper confirmation checks before executing this tool.

This MCP Server handles corpus documents and metadata. The entire interaction stays within the isolated sandbox environment, meaning only the necessary tools are exposed to your workflow agent.

You first run `list_corpora` to get all names. Then you can target those specific keys with `perform_semantic_search` to test the scope of your data.

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