How to Use the DeepInfra (Serverless LLM Inference) MCP in Windsurf

Q: How do I configure DeepInfra (Serverless LLM Inference) in Windsurf?

Open /.codeium/windsurf/mcpconfig.json and add your Vinkius endpoint URL under the mcpServers key. Cascade detects the new tools the moment you click refresh in the MCP panel.

Q: Can Windsurf run image generation through DeepInfra (Serverless LLM Inference)?

It handles this natively. Cascade calls the generateimage tool with your specific text prompt, receives the base64 output, and saves the file directly to your active workspace.

Connect Windsurf to serverless LLMs, custom embeddings, and image generation models via Vinkius.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepInfra (Serverless LLM Inference) MCP to Windsurf

Create your Vinkius account to connect DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query External Models Directly

The `create_chat_completion` tool lets Cascade query external LLMs like DeepSeek-V3 straight from your editor. You pass the exact model string and a messages array, and the agent handles the API request. Instead of pasting code into a browser window, your AI client pulls the response and applies the logic right into your open files. Cascade figures out the context, asks the external model for a solution, and writes the diff.

Generate Visual Assets

Calling `generate_image` allows Windsurf to build visual assets while writing your frontend code. You describe the graphic you need, and the agent forwards the prompt to the serverless infrastructure. Cascade spots a missing hero image in your React component, requests it from the API, and saves the resulting asset to your public folder. You get actual files generated and placed without leaving the IDE.

Run Specialized Inference via MCP Server

Using `run_native_inference` gives this MCP Server access to specialized models outside standard chat specs. You target specific endpoints for tasks like speech-to-text or OCR processing. If your project needs custom video generation or hits a private deployment, Cascade hits the exact endpoint you specify. The agent parses the raw JSON output and integrates the data into your application logic automatically.

Setup guide

Set up DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) payment history." If connected, Cascade will call the DeepInfra (Serverless LLM Inference) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "deepinfra-serverless-llm-inference-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 DeepInfra. 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 DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) MCP in Windsurf

Open ~/.codeium/windsurf/mcp_config.json and add your Vinkius endpoint URL under the mcpServers key. Cascade detects the new tools the moment you click refresh in the MCP panel.

It handles this natively. Cascade calls the generate_image tool with your specific text prompt, receives the base64 output, and saves the file directly to your active workspace.

You pass the exact model string, like deepseek-ai/DeepSeek-V3, in the request. The server routes that string to the corresponding serverless endpoint.

This setup lets your agent query specialized open-source models for highly specific tasks. You get access to custom embeddings and native inference pipelines that standard editor assistants lack.

Your text prompts and codebase snippets route through an ephemeral V8 Isolate Sandbox. Vinkius drops the runtime memory immediately after passing the payload to the external API, leaving zero traces of your proprietary code.

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