How to Use the Vectara MCP in Claude

Q: How do I list my existing datasets with Vectara and Claude Desktop?

You use the listcorpora tool. It lists all available corpora in your account, letting you see exactly what data is indexed for your agent to use.

Q: What kind of documents can I delete using Vectara and Claude Desktop?

The deletecorpusdocument tool permanently removes a single document from a corpus. Remember, this action cannot be undone, so make sure you confirm the document ID first.

Q: Can I see my past chat sessions using Vectara and Claude Desktop?

Yes, calling listchatsessions shows all previous RAG chats. This is handy for tracking who asked what and when, letting you audit the AI’s usage.

Q: If I update data, how do I confirm it in Vectara and Claude Desktop?

After updating sources, run listcorpusdocuments for a specific corpus. This confirms that the new documents have been indexed and are ready for your agent to use.

Access your internal knowledge base directly from the Claude Desktop app or web browser.

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 Claude Desktop

Create your Vinkius account to connect Vectara to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounding Chats with the MCP Server

You get an immediate, summarized AI response when you run `execute_rag_chat`. Just provide a corpus key and your query, and the agent returns citations alongside the answer. It’s way better than general chat because it only uses your company's documents.

Managing Your Knowledge Sources

Need to know what data you have? Use `list_corpora` to see every dataset stored in the Vectara account. You can also check metadata and setup for any specific knowledge base by calling `get_corpus_details`. It gives you a full picture of your sources.

Precise Data Retrieval

Don't just rely on chat. Run `perform_semantic_search` to execute deep searches across multiple corpora using comma-separated keys and your query text. This tool returns the raw, relevant documents so you can read exactly what the AI used.

Setup guide

Set up Vectara MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Vectara MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Vectara MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under vectara-mcp.

json

{
  "mcpServers": {
    "vectara-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

You use the `list_corpora` tool. It lists all available corpora in your account, letting you see exactly what data is indexed for your agent to use.

The `delete_corpus_document` tool permanently removes a single document from a corpus. Remember, this action cannot be undone, so make sure you confirm the document ID first.

Yes, calling `list_chat_sessions` shows all previous RAG chats. This is handy for tracking who asked what and when, letting you audit the AI’s usage.

The desktop app lets your agent reach your local filesystem and databases on localhost. This means you don't need to upload files; the tools work directly with what’s on your machine.

After updating sources, run `list_corpus_documents` for a specific corpus. This confirms that the new documents have been indexed and are ready for your agent to use.

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