How to Use the watsonx Discovery MCP in Windsurf

Q: How do I verify the connection between watsonx Discovery and Windsurf?

You check component health with getcomponentsettings to confirm that all necessary project components are active. This gives you confidence before running deep data queries.

Connect watsonx Discovery to Windsurf for autonomous data querying and analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect watsonx Discovery MCP to Windsurf

Create your Vinkius account to connect watsonx Discovery to Windsurf 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 watsonx Discovery with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Querying Data with the MCP Server

Need to find something specific? You run a natural language or DQL query against any collection using `query_discovery_content`. Cascade takes your goal, figures out which collections you need to check, and executes the search. It returns direct insights based on watsonx Discovery's cognitive engine.

Managing Data Collections in Windsurf

Before searching, you have to know what data exists. You can list all available buckets with `list_discovery_collections` and check the documents inside a specific one using `list_collection_documents`. This lets Cascade map out your data landscape before running any queries.

Checking Data Processing Status

Data isn't just stored; it gets processed. You can see what NLP models are applied to documents using `list_available_enrichments`. Plus, you get a health check on the project setup with `get_component_settings` and retrieve metadata for single files via `get_document_details`.

Setup guide

Set up watsonx Discovery MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the watsonx Discovery 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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my watsonx Discovery payment history." If connected, Cascade will call the watsonx Discovery tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "watsonx-discovery-mcp": {
      "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 watsonx Discovery. 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 watsonx Discovery 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 watsonx Discovery MCP in Windsurf

Just give Cascade a goal—for instance, 'Find all documents mentioning Q3 revenue.' It uses the `query_discovery_content` tool to run the natural language query against your defined collections. You get the results directly without writing any code.

This MCP Server handles structured and unstructured documents within various indexed collections. It focuses on providing AI-powered insights into complex, diverse corporate data sources.

Yes. The server supports both natural language queries and DQL (Discovery Query Language) via `query_discovery_content`. This means you can search using plain English or specific query syntax.

You check component health with `get_component_settings` to confirm that all necessary project components are active. This gives you confidence before running deep data queries.

The server primarily interacts with document metadata and collection IDs. It reads the configuration settings for these resources, ensuring your agent works only on authorized project components.

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