How to Use the watsonx Discovery MCP in Mastra AI

Q: Can I check document status for my pipeline with watsonx Discovery and Mastra AI?

Yes. The getdocumentdetails tool retrieves metadata and current operational status for any indexed document, which is crucial for determining if a workflow step can proceed.

Q: What data sources are available to watsonx Discovery when using Mastra AI?

You start by calling listdiscoverycollections. This function lists all the distinct data collections within your project, allowing you to programmatically select the correct target for any operation.

Q: Does watsonx Discovery support complex queries in Mastra AI?

It does. The querydiscoverycontent tool supports both natural language and DQL queries, giving your workflow engine powerful search capabilities within the data collection.

Build reliable multi-step workflows with Mastra AI that handle failures gracefully.

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 Mastra AI

Create your Vinkius account to connect watsonx Discovery to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinating Data Queries in Mastra AI

Use the `query_discovery_content` tool to execute a search query against watsonx Discovery. You can place this action within a workflow step—for instance, checking data before notifying an admin. If the initial query fails, your Mastra AI workflow automatically retries with backoff, ensuring your process completes even if the network hiccups.

Validating System Health with MCP Server

Before running a critical step, use `get_component_settings` to retrieve the configuration and health status of project components. This builds reliability right into your workflow logic. You can also check specific document readiness using `get_document_details`, making sure only verified data feeds into your final action.

Defining Data Scope with MCP Server

Need to make sure the right context is used? First, call `list_discovery_collections` to see every available resource. Then, you can check what NLP models are running by listing enrichments using `list_available_enrichments`. These steps ensure your complex workflow always targets the correct data and has the necessary processing enabled.

Setup guide

Set up watsonx Discovery MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All watsonx Discovery tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "watsonx-discovery-mcp-client",
  servers: {
    "watsonx-discovery-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "watsonx Discovery Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to watsonx Discovery tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent watsonx Discovery transactions"
);
console.log(result.text);

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 Mastra AI

You treat the MCP server tools as callable steps in your workflow engine. You can define conditional branching: if the `query_discovery_content` fails, you route the process to a different retry step.

Yes. The `get_document_details` tool retrieves metadata and current operational status for any indexed document, which is crucial for determining if a workflow step can proceed.

You start by calling `list_discovery_collections`. This function lists all the distinct data collections within your project, allowing you to programmatically select the correct target for any operation.

It does. The `query_discovery_content` tool supports both natural language and DQL queries, giving your workflow engine powerful search capabilities within the data collection.

The server touches document metadata and component settings. Specifically, it reads details about the status of individual indexed documents when running a workflow step.

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