How to Use the Verba MCP in Claude Code

Q: How can I automate knowledge queries with Verba and Claude Code?

Call performragquery within your shell script. This tool runs the RAG search, returning summarized answers with citations directly to standard output. It's built for headless execution.

Q: What is the process for adding new data using Verba and Claude Code?

The addknowledgedocument tool handles this. You pass in the document content and required metadata JSON directly from your script's variables. The MCP Server indexes it immediately.

Q: Can I check all indexed documents using Verba? (Claude Code)

Yes, you use listknowledgedocuments. This tool provides a list of every document ID and title currently stored in the knowledge base for auditing purposes.

Q: If I need to validate the whole setup, what should I check? (Verba/Claude Code)

You can run getsystemconfig to pull the current operational settings from Verba. This is a key step for validating that your deployment environment is correct before running any main jobs.

Automate knowledge workflows in CI/CD pipelines using Verba with Claude Code's headless execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Verba MCP to Claude Code

Create your Vinkius account to connect Verba 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 Verba with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Programmatic Document Ingestion

Use `add_knowledge_document` to feed content into the knowledge base from a script. You pass in the document text and optional metadata JSON directly. The system also supports removing files via `delete_knowledge_document`. Be aware that this operation is permanent when running through your automated shell scripts.

Automated Knowledge Retrieval

`perform_rag_query` executes the RAG search against Verba. This tool returns summarized answers and includes citations, making it ideal for generating reports in a pipeline. The `get_document_details` function allows you to pull the full content and metadata of any single document ID programmatically.

System Status Checks

`list_knowledge_documents` outputs an exhaustive list of all documents indexed in Verba. This is perfect for pre-run validation in a CI/CD job. Alternatively, `get_system_config` retrieves the current operating configuration from the MCP Server, ensuring your pipeline environment is set up correctly.

Setup guide

Set up Verba 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 verba-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http verba-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 Verba 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": {
    "verba-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 Verba. 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 Verba 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 Verba MCP in Claude Code

Call `perform_rag_query` within your shell script. This tool runs the RAG search, returning summarized answers with citations directly to standard output. It's built for headless execution.

The `add_knowledge_document` tool handles this. You pass in the document content and required metadata JSON directly from your script's variables. The MCP Server indexes it immediately.

Yes, you use `list_knowledge_documents`. This tool provides a list of every document ID and title currently stored in the knowledge base for auditing purposes.

The Verba system manages structured text documents and their associated metadata JSON. It processes these assets to generate contextual answers via RAG.

You can run `get_system_config` to pull the current operational settings from Verba. This is a key step for validating that your deployment environment is correct before running any main jobs.

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