How to Use the IBM watsonx MCP in Cursor

Q: How do I configure the IBM watsonx MCP server in Cursor?

Create a .cursor/mcp.json file in your project root and add the server config. Cursor automatically detects the new tools like generatetext for your agent sessions.

Q: Can Cursor automate model tuning on IBM watsonx?

Yes, the editor's agent can call startmodeltuning using a data URL you provide. You can then monitor the progress directly in your terminal using the gettuningstatus tool.

Q: How does Cursor use IBM watsonx embeddings during development?

The editor runs generateembeddings to convert code snippets or documentation into vectors. This lets Cursor test similarity search logic without leaving your active workspace.

Q: Can I inspect model specifications within Cursor using IBM watsonx?

Yes, you can ask Cursor to run getmodeldetails to check context windows or lifecycle states. This ensures your code targets compatible parameters.

Build code that uses IBM watsonx models and embeddings directly inside your Cursor editor.

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 Cursor

Create your Vinkius account to connect IBM watsonx to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate embeddings inside your Cursor editor

The `generate_embeddings` tool lets Cursor create vector representations of your codebase on the fly. You don't have to write custom python scripts just to test how your text chunks embed. Having this capability inside your editor means you can build semantic search features faster. Cursor calls the tool, receives the vectors, and injects them straight into your active code file.

Run multi-turn chat models while you code

Using the `generate_chat` tool, Cursor pulls conversational responses directly from your IBM cloud setup. This lets the editor's agent mode test chat flows using live model responses instead of mock data. If you need to switch models, the `list_models` tool displays what's active in your account. You can swap targets without leaving your cursor-agent workflow.

Manage prompt templates with this MCP Server

Keeping your prompt files in sync with your cloud environment is simple when Cursor uses the `list_prompts` tool. You pull the latest templates from your IBM project straight into your editor sidebar. When you modify a prompt locally, the `create_prompt` tool pushes the updated version back to your account. This prevents version drift between your local codebase and your cloud templates.

Setup guide

Set up IBM watsonx MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the IBM watsonx MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent IBM watsonx transactions." If the MCP tools are loaded correctly, Cursor will call the IBM watsonx tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "ibm-watsonx-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 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 Cursor

Create a `.cursor/mcp.json` file in your project root and add the server config. Cursor automatically detects the new tools like `generate_text` for your agent sessions.

Yes, the editor's agent can call `start_model_tuning` using a data URL you provide. You can then monitor the progress directly in your terminal using the `get_tuning_status` tool.

The editor runs `generate_embeddings` to convert code snippets or documentation into vectors. This lets Cursor test similarity search logic without leaving your active workspace.

Yes, you can ask Cursor to run `get_model_details` to check context windows or lifecycle states. This ensures your code targets compatible parameters.

Your credentials stay in your local environment variables or Vinkius vault. Cursor never exposes your vector embeddings or prompt parameters to third-party servers.

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