How to Use the IBM watsonx MCP in Mastra AI

Q: How do I register the IBM watsonx MCP Server tools with a Mastra AI agent?

Instantiate the MCP client from @mastra/mcp with your server URL. Get the tools with mcpClient.listTools() and spread them into your agent's tools array.

Q: Can Mastra AI handle long-running tuning jobs on IBM watsonx?

Yes, Mastra uses its built-in workflow engine to poll gettuningstatus at set intervals. This prevents your execution thread from blocking while waiting for the model to finish training.

Q: Does Mastra AI support human approval for IBM watsonx prompt creation?

Yes, you use the requireToolApproval setting on the createprompt tool. This forces the agent to pause and ask for confirmation before saving the prompt.

Build resilient agent workflows with Mastra AI and the IBM watsonx MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBM watsonx MCP to Mastra AI

Create your Vinkius account to connect IBM watsonx 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 IBM watsonx with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Tuning IBM watsonx Models inside Mastra AI Workflows

The `start_model_tuning` tool kicks off custom tuning jobs for your foundation models directly from a Mastra AI workflow step using this MCP tool. You point the tool to your cloud training data, and Mastra's engine tracks the execution. If the tuning job fails, Mastra's automatic retry logic with exponential backoff triggers a retry. The workflow pauses until `get_tuning_status` reports a successful completion before moving to the next deployment step.

Conditional Routing Based on Embeddings

The `generate_embeddings` tool generates vector representations of your incoming user queries. Mastra AI uses these vectors to route tasks dynamically to different specialized sub-agents. You write conditional branches that check the semantic similarity of the text. If the query aligns with a technical topic, Mastra routes it to a model fetched via `get_model_details` that handles complex logic.

Human-in-the-Loop Prompt Creation

The `create_prompt` tool saves new prompt templates directly into your watsonx project workspace. In Mastra AI, you hook this tool to a manual approval step using the framework's human-in-the-loop feature. An operator must approve the template before the system saves it. This guarantees that no unverified or broken prompt templates end up in your production project environment.

Setup guide

Set up IBM watsonx 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 IBM watsonx 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: "ibm-watsonx-mcp-client",
  servers: {
    "ibm-watsonx-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent IBM watsonx 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 IBM watsonx. 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 IBM watsonx 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 IBM watsonx MCP in Mastra AI

Instantiate the MCP client from `@mastra/mcp` with your server URL. Get the tools with `mcpClient.listTools()` and spread them into your agent's tools array.

Yes, Mastra uses its built-in workflow engine to poll `get_tuning_status` at set intervals. This prevents your execution thread from blocking while waiting for the model to finish training.

Yes, you use the `requireToolApproval` setting on the `create_prompt` tool. This forces the agent to pause and ask for confirmation before saving the prompt.

Mastra's workflow engine has built-in retry mechanisms. If a tool like `generate_text` hits an API rate limit, the system backs off and retries automatically.

Your training dataset URLs and tuning configurations are sent directly to your IBM Cloud account. Vinkius handles the credentials securely using single-endpoint tokens and never caches your dataset files.

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