An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect watsonx Discovery 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. Turn unstructured data into actionable intelligence 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 watsonx Discovery.

  1. 01

    Get document details

    This capability pulls metadata and current status for a specific indexed document.

  2. 02

    List collection documents

    Use this to see every document currently indexed within a specific collection.

  3. 03

    List discovery collections

    This capability returns a list of all data collections inside your current watsonx Discovery project.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through watsonx Discovery.

  1. 04

    Query discovery content

    This capability executes natural language or DQL queries against a specific collection ID to find relevant content.

  2. 05

    Get component settings

    Use this to check the configuration and health status of your project components.

  3. 06

    List available enrichments

    This capability lists the NLP models, like Sentiment or Entities, that are active in your project.

Real work

What teams actually run

01

Automated Knowledge Retrieval

An analyst asks the agent to find specific clauses within thousands of legal PDFs.

02

Data Pipeline Monitoring

A developer checks the ingestion status and component health via chat instead of a dashboard.

03

NLP Audit

A data scientist verifies which entities or sentiment models are being applied to new documents.

04

Semantic Content Discovery

A product team uses semantic search to find patterns in unstructured customer feedback datasets.

Automate a task

Put watsonx Discovery 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

watsonx Discovery 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 watsonx Discovery 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

952ms average. Fast in production.

watsonx Discovery is checked daily against the live service.

Daily averagePeak 1253ms
Oct 3Today
Fastest day
655ms
Slowest day
1253ms
14-day trend
Slowing+9%

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 watsonx Discovery, so you can see the experience inside your AI.

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

watsonx Discovery Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_MOvCoAeU4n0XLtoAj5AMd7HKRadaRJgAFtxeD6Bh/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 — watsonx Discovery capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "watsonx-discovery-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_MOvCoAeU4n0XLtoAj5AMd7HKRadaRJgAFtxeD6Bh/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 watsonx Discovery in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work watsonx Discovery owners hand off.

This MCP is built for professionals managing large-scale enterprise knowledge bases who need to interact with data without manual console navigation.

  • 01

    Enterprise Developers

    They use the MCP to build grounded AI applications using semantic search and ingestion pipelines.

  • 02

    Knowledge Analysts

    They use the agent to surface information from document repositories and audit NLP enrichments.

  • 03

    Data Scientists

    They use the chat interface to test DQL queries and monitor data ingestion status.

FAQ

Questions watsonx Discovery owners ask.

  • 01

    How do I connect watsonx Discovery to my AI client?

    You subscribe to the MCP on Vinkius and provide your watsonx URL, API Key, and Project ID. Once connected, you can use it in any MCP-compatible client like Claude or Cursor.

  • 02

    Can I use DQL queries with this MCP?

    Yes. The query_discovery_content capability supports both natural language and Discovery Query Language (DQL) for precise searches.

  • 03

    What kind of unstructured data can I search?

    The MCP allows you to perform semantic searches across any data collections indexed within your watsonx Discovery project.

  • 04

    Does this MCP support NLP enrichments?

    Yes. You can use the list_available_enrichments capability to see which NLP models, such as Sentiment or Entities, are active in your project.

  • 05

    Where is the data hosted?

    The MCP connects to your existing IBM watsonx Discovery project. Vinkius hosts the connector and manages the connection to your IBM environment.

  • 06

    Can I query my data collections using natural language?

    Yes. The query_discovery_content capability allows your AI agent to perform natural language queries against your watsonx Discovery collections, returning highly relevant results based on IBM's cognitive search engine.

  • 07

    How do I see what NLP models are being applied to my documents?

    Use the list_available_enrichments capability to see all NLP enrichments (like Sentiment, Entity Extraction, or Category Classification) configured for your project and applied during the ingestion pipeline.

  • 08

    Can I monitor the ingestion status of a specific document?

    Absolutely. Using the get_document_details capability, you can check the ingestion status and technical metadata for any specific document ID, ensuring your data is correctly indexed and searchable.

Explore

More in Industry Titans

Suggestions

Connect watsonx Discovery to Claude, Cursor, ChatGPT & more