How to Use the Vectara MCP in Claude Code

Q: How do I connect Vectara with Claude Code?

Run the connection command: claude mcp add --transport http -- . This sets up headless access, making all MCP Server tools available to your scripts.

Q: Can I list all corpora using Vectara in Claude Code?

Yes. You can execute listcorpora as part of your pipeline script to programmatically discover every dataset available in the account before running the main job.

Q: Does MCP Server support data deletion for Claude Code?

The tool deletecorpusdocument allows permanent removal. This command is highly sensitive and must be wrapped safely within your CI/CD scripting to prevent accidental loss of indexed documents.

Automate pipelines with Claude Code using Vectara's headless RAG tools via the terminal.

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 Code

Create your Vinkius account to connect Vectara to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Running Grounded Chat in Pipelines

Script a chat completion that relies on external data. `execute_rag_chat` takes corpus keys and your query, returning an AI summary with citations. You pipe this command into a CI/CD script to get verifiable, source-backed answers without needing any graphical interface.

Batch Semantic Search

Need to check data across multiple sources? Use `perform_semantic_search`. Pass one or more comma-separated corpus keys and the query text directly from your script. This function is perfect for cron jobs that need to cross-reference information held in several different datasets.

Auditing Corpus Structure

Verify your data structure before running a job. `get_corpus_details` retrieves the configuration and metadata for a specific corpus, allowing you to script checks. Alternatively, use `list_chat_sessions` to log and verify previous RAG chat interactions within your terminal workflow.

Setup guide

Set up Vectara MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see vectara-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Vectara transactions." It will automatically discover and invoke the available Vectara tools.

Terminal

claude mcp add --transport http vectara-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Vectara MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "vectara-mcp": {
      "type": "url",
      "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 Code

Run the connection command: `claude mcp add --transport http -- `. This sets up headless access, making all MCP Server tools available to your scripts.

Vectara handles the interaction with corpus keys and document content. Since it runs in a terminal context, everything is processed via standard input/output streams.

Yes. You can execute `list_corpora` as part of your pipeline script to programmatically discover every dataset available in the account before running the main job.

The tool `delete_corpus_document` allows permanent removal. This command is highly sensitive and must be wrapped safely within your CI/CD scripting to prevent accidental loss of indexed documents.

It processes textual metadata and the content of indexed documents. The scope remains focused on structured text datasets, making it ideal for scriptable tasks.

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