An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Verba to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage and query your Weaviate knowledge base through chat.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Verba.

  1. 01

    Delete knowledge document

    This capability permanently removes a document from your knowledge base. Use it when you need to purge outdated or incorrect information.

  2. 02

    Get document details

    This capability pulls the full content and metadata for a specific document. It's useful when you need to inspect the raw data behind an ID.

  3. 03

    List knowledge documents

    This capability provides a list of every document currently indexed in your Verba knowledge base.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Verba.

  1. 04

    Add knowledge document

    This capability ingests new text and metadata into your knowledge base. You can feed new context to your agent by providing document content and JSON metadata.

  2. 05

    Get system config

    This capability retrieves your current Verba system settings. Use it to verify which embedding models or local LLM connections are active.

  3. 06

    Perform rag query

    This capability runs a RAG query against your knowledge base. It returns summarized answers that include specific document citations.

Real work

What teams actually run

01

Testing Embedding Fidelity

A developer adds a new document chunk and immediately runs a query to see how the embedding model handles the new data.

02

Technical Manual Querying

A manager asks for specific deployment steps from a massive technical guide and receives a cited summary.

03

Knowledge Base Maintenance

An admin identifies an outdated document and uses a command to remove it from the index.

04

System Debugging

A user checks the Verba configuration to ensure the correct local LLM connection is active.

Automate a task

Put Verba to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Verba works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Verba to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

891ms average. Fast in production.

Verba is checked daily against the live service.

Daily averagePeak 1214ms
Oct 3Today
Fastest day
669ms
Slowest day
1214ms
14-day trend
Slowing+5%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Verba, so you can see the experience inside your AI.

It does not authenticate your account with Verba. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Verba Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_mosNtker0LQyevIfUh7gGdgJqJOKEbbiUG4YbxIE/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Verba capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "verba-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_mosNtker0LQyevIfUh7gGdgJqJOKEbbiUG4YbxIE/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Verba in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Verba owners hand off.

This MCP is built for people working directly with RAG architectures and large document sets.

  • 01

    RAG Developers

    They use the MCP to quickly add or delete text chunks to test embedding fidelity during coding sessions.

  • 02

    Knowledge Managers

    They query dense technical manuals using semantic search to get verified text snippets.

  • 03

    Open Source Hobbyists

    They use it to manage personal Weaviate or Verba stacks through a programmatic chat layer.

FAQ

Questions Verba owners ask.

  • 01

    How do I connect Verba to my AI client?

    You need to provide your Verba API URL and your API Key to the MCP. Once configured, you can use any MCP-compatible client like Claude or Cursor.

  • 02

    Can I delete documents using this MCP?

    Yes, you can use the delete_knowledge_document capability to permanently remove a document from your knowledge base.

  • 03

    Does this MCP provide citations for its answers?

    Yes, when you perform a RAG query, the agent returns summarized answers that include specific document citations.

  • 04

    What kind of system information can I check?

    You can use the get_system_config capability to check your embedding models, local LLM connections, and overall cluster health.

  • 05

    Is this compatible with Cursor or Windsurf?

    Yes, this MCP works with any MCP-compatible client, including Cursor and Windsurf.

  • 06

    Can I query my local Verba instance directly through Cursor?

    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.

  • 07

    How do I insert fresh text data into Verba completely using conversational chat?

    Provide the agent with your desired context directly. For example: Add this chunk of markdown as a new document to Verba: '# Title Content...'. The agent leverages addDocumentTool, serializes the payload, and commits it into Verba's vector store immutably.

  • 08

    Are the query answers backed by citations from its embedded documents?

    Absolutely. That's the primary benefit of the integration. When you run perform_rag_query, Verba utilizes Weaviate's hybrid search mechanics. The output explicitly includes natural language synthesis backed by the unique document IDs and snippet texts it referenced.

Explore

More in Knowledge Management

Suggestions

Connect Verba to Claude, Cursor, ChatGPT & more