2,500+ MCP servers ready to use
Vinkius

Nyckel ML MCP Server for Windsurf 10 tools — connect in under 2 minutes

Built by Vinkius GDPR 10 Tools IDE

Windsurf brings agentic AI coding to a purpose-built IDE. Connect Nyckel ML through Vinkius and Cascade will auto-discover every tool. ask questions, generate code, and act on live data without leaving your editor.

Vinkius supports streamable HTTP and SSE.

RecommendedModern Approach — Zero Configuration

Vinkius Desktop App

The modern way to manage MCP Servers — no config files, no terminal commands. Install Nyckel ML and 2,500+ MCP Servers from a single visual interface.

Vinkius Desktop InterfaceVinkius Desktop InterfaceVinkius Desktop InterfaceVinkius Desktop Interface
Download Free Open SourceNo signup required
Classic Setup·json
{
  "mcpServers": {
    "nyckel-ml": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}
Nyckel ML
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Nyckel ML MCP Server

Connect your Nyckel machine learning account to your AI agent and leverage powerful automated classification and semantic search through natural conversation.

Windsurf's Cascade agent chains multiple Nyckel ML tool calls autonomously. query data, analyze results, and generate code in a single agentic session. Paste Vinkius Edge URL, reload, and all 10 tools are immediately available. Real-time tool feedback appears inline, so you see API responses directly in your editor.

What you can do

  • Automated Classification — Send text or image URLs to your trained ML functions to get instant predictions and confidence scores.
  • Semantic Search — Query your search function galleries to find semantically similar samples based on input data.
  • Function Management — List all ML functions in your account and retrieve detailed configuration and metadata.
  • Training Oversight — Access the data samples used to train your functions and monitor assigned labels.
  • Sample Annotation — Upload new training samples and manually assign or update classification labels.
  • Label Discovery — Retrieve the set of all available labels and categories defined for your ML models.
  • Account Insights — Access profile and workspace metadata for your authenticated Nyckel account.

The Nyckel ML MCP Server exposes 10 tools through the Vinkius. Connect it to Windsurf in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Nyckel ML to Windsurf via MCP

Follow these steps to integrate the Nyckel ML MCP Server with Windsurf.

01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"

02

Add the server

Paste the JSON configuration above into mcp_config.json

03

Save and reload

Windsurf will detect the new server automatically

04

Start using Nyckel ML

Open Cascade and ask: "Using Nyckel ML, help me...". 10 tools available

Why Use Windsurf with the Nyckel ML MCP Server

Windsurf provides unique advantages when paired with Nyckel ML through the Model Context Protocol.

01

Windsurf's Cascade agent autonomously chains multiple tool calls in sequence, solving complex multi-step tasks without manual intervention

02

Purpose-built for agentic workflows. Cascade understands context across your entire codebase and integrates MCP tools natively

03

JSON-based configuration means zero code changes: paste a URL, reload, and all 10 tools are immediately available

04

Real-time tool feedback is displayed inline, so you see API responses directly in your editor without switching contexts

Nyckel ML + Windsurf Use Cases

Practical scenarios where Windsurf combined with the Nyckel ML MCP Server delivers measurable value.

01

Automated code generation: ask Cascade to fetch data from Nyckel ML and generate models, types, or handlers based on real API responses

02

Live debugging: query Nyckel ML tools mid-session to inspect production data while debugging without leaving the editor

03

Documentation generation: pull schema information from Nyckel ML and have Cascade generate comprehensive API docs automatically

04

Rapid prototyping: combine Nyckel ML data with Cascade's code generation to scaffold entire features in minutes

Nyckel ML MCP Tools for Windsurf (10)

These 10 tools become available when you connect Nyckel ML to Windsurf via MCP:

01

annotate_ml_sample

Assign label to a sample

02

create_ml_sample

Add a training sample

03

delete_ml_function

Delete an ML function

04

get_account_info

Get current account info

05

get_ml_function

Get specific function info

06

invoke_ml_function

Classify data using a function

07

list_ml_functions

) in your account. List all ML functions

08

list_ml_labels

List available labels

09

list_ml_samples

List training samples

10

semantic_search

Perform semantic search

Example Prompts for Nyckel ML in Windsurf

Ready-to-use prompts you can give your Windsurf agent to start working with Nyckel ML immediately.

01

"Classify this text: 'The delivery was very late and the food was cold' using function ID 'func_123'."

02

"Search my product gallery for an image similar to 'https://example.com/shoe.jpg' using function 'func_search_99'."

03

"List all the machine learning functions in my Nyckel account."

Troubleshooting Nyckel ML MCP Server with Windsurf

Common issues when connecting Nyckel ML to Windsurf through the Vinkius, and how to resolve them.

01

Server not connecting

Check Settings → MCP for the server status. Try toggling it off and on.

Nyckel ML + Windsurf FAQ

Common questions about integrating Nyckel ML MCP Server with Windsurf.

01

How does Windsurf discover MCP tools?

Windsurf reads the mcp_config.json file on startup and connects to each configured server via Streamable HTTP. Tools are listed in the MCP panel and available to Cascade automatically.
02

Can Cascade chain multiple MCP tool calls?

Yes. Cascade is an agentic system. it can plan and execute multi-step workflows, calling several tools in sequence to accomplish complex tasks without manual prompting between steps.
03

Does Windsurf support multiple MCP servers?

Yes. Add as many servers as needed in mcp_config.json. Each server's tools appear in the MCP panel and Cascade can use tools from different servers in a single flow.

Connect Nyckel ML to Windsurf

Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.