Verba

Verba MCP Connector for Claude

A+

Connect your Verba RAG platform to your AI agent. Search your documents, retrieve semantic answers, and manage your Weaviate knowledge base directly.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Intertwine the open-source Verba (by Weaviate) ecosystem natively into your conversational AI IDE. Execute powerful Retrieval-Augmented Generation processes and manage your localized knowledge bases simply by chatting.

What you can do

  • Augmented Queries — Cast a question to your agent and have it retrieve fully synthesized answers from the Verba engine completely backed up by exact document citations.
  • Knowledge Management — Insert new context text, list all ingested documents, retrieve the deeply embedded raw data of any ID, or remove dead knowledge dynamically without Web UIs.
  • Health Checks — Request system configurations directly via chat to ensure your local LLM connections, embedding models, and cluster health are firing effectively.

How it works

  1. Ensure your local or cloud Verba instance is running
  2. Supply your Verba API URL and API Key (if authenticated)
  3. Ask Claude or Cursor to query, retrieve, or insert document structures intuitively.

Who is this for?

  • RAG Developers — quickly add or delete text chunks to evaluate changes in embedding fidelity directly inside your IDE coding session.
  • Knowledge Managers — query your dense technical manuals using semantic search and receive the verified text snippets instantly.
  • Open Source Hobbyists — orchestrate your personal Weaviate/Verba RAG stacks strictly through the programmatic conversational layer.
ragsemantic-searchdocument-ingestionknowledge-baseopen-sourceretrieval-augmented-generation

6 tools expose this connector's capabilities to your AI agent.

add_knowledge_document

Provide the document content and optional metadata JSON. Ingests a new document into the Verba knowledge base

delete_knowledge_document

This action is irreversible. Permanently removes a document from the knowledge base

get_document_details

Retrieves the full content and metadata of a specific document

get_system_config

Retrieves the current Verba system configuration

list_knowledge_documents

Lists all documents indexed in the Verba knowledge base

perform_rag_query

Returns summarized answers with citations. Executes a RAG (Retrieval Augmented Generation) query against the Verba knowledge base

See how to talk to your AI agent using Verba.

Check Verba's configuration to see which embedding model it is currently using.

I've retrieved your Verba system configuration. The engine is properly spun up and indicates that it is currently utilizing the 'MiniLM-v12' embedding model localized naturally. All systems appear nominal for retrieval.

Perform a RAG query asking: 'What are our key deployment steps based on the infrastructure guide?'

Result from Verba Knowledge Base: *"According to the 'Infrastructure Deployment v2' document, there are three key steps for deployment: 1) Initiate pre-flight health checks via CI/CD, 2) Provision ephemeral node pods for shadow tests, and 3) Cutover traffic using a blue-green weighting swap mechanism."* *(Source Citations: DocId: xfA-21v - confidence: 0.96)*

List all documents and output the unique ID of the 'Employee Code of Conduct' file.

I've queried the document catalog. You have 15 items overall. The specific 'Employee Code of Conduct' document is indexed under the Document ID `5fcbeb99-xxxx`. Would you like me to delete it or replace its contents with a new updated chunk?

Yes! Once you configure `VERBA_API_URL` to point to `http://localhost:8000` (or your host port), you can prompt your AI assistant to execute rigorous `perform_rag_query` instructions without ever breaking your developer focus.

Related Connectors