How to Use the Fireworks AI MCP in Windsurf

Q: Can I use Fireworks AI to search my codebase in Windsurf?

Yes. Cascade uses the embed tool to generate vectors of your local files. This lets your agent run semantic searches across your repository to find relevant context before initiating a code refactor.

Q: How do I run image generation within my Windsurf workspace?

You tell Cascade to create an image, and it invokes the image tool. The agent handles the API call, receives the generated image, and saves it directly to your workspace folder.

Q: How does the Fireworks AI MCP server handle my audio and text data privacy in Windsurf?

All your audio files sent to the transcribe tool and text prompts sent to the chat tool go directly to the secure Vinkius sandbox. Your raw data is never stored or used for training, keeping your intellectual property completely isolated.

Run ultra-fast open-weights models and audio transcription directly inside your Windsurf Cascade workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fireworks AI MCP to Windsurf

Create your Vinkius account to connect Fireworks AI 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 Fireworks AI with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous model discovery for Windsurf Cascade

The `list_models` tool lets Cascade scan every available Fireworks AI endpoint the moment you connect this MCP server. This means your autonomous agent knows exactly which open-weights model to choose for a specific coding task without you having to hardcode model names in your settings. Cascade uses this real-time list to spin up multi-step plans. It switches models on the fly depending on whether you need a fast reasoning step or a massive context window for debugging.

Fast text generation and code completion

The `chat` tool connects Cascade directly to high-throughput inference engines to generate code blocks in milliseconds. Instead of waiting for sluggish proprietary APIs, your agent runs its generation steps using optimized open-source weights. For simpler text tasks, the `completion` tool handles raw prompt execution without the overhead of chat templates. Cascade chains these operations together to write documentation, draft pull requests, and refactor files in one autonomous run.

Generate assets and transcribe audio in Cascade

The `image` tool lets Cascade generate visual assets directly within your workspace for UI prototyping. If your frontend code needs a placeholder asset, the agent calls the image generation endpoint and saves the file to your project directory. Along with that, the `transcribe` tool converts voice notes into markdown specifications, while the `embed` tool creates vector representations of your codebase. This allows Cascade to search your local files with semantic precision before writing a single line of code.

Setup guide

Set up Fireworks AI 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 Fireworks AI 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 Fireworks AI payment history." If connected, Cascade will call the Fireworks AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "fireworks-ai-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 Fireworks AI. 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 Fireworks AI 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 Fireworks AI MCP in Windsurf

It routes your text requests through highly optimized GPU clusters using the `chat` tool. Cascade gets responses in a fraction of the time compared to standard endpoints, allowing it to chain multiple code-generation steps without lagging.

Yes. Cascade uses the `embed` tool to generate vectors of your local files. This lets your agent run semantic searches across your repository to find relevant context before initiating a code refactor.

It does. Once you add the MCP server to your configuration file, Cascade queries the `list_models` tool on startup. The agent instantly understands what endpoints are available and begins calling them as needed.

You tell Cascade to create an image, and it invokes the `image` tool. The agent handles the API call, receives the generated image, and saves it directly to your workspace folder.

All your audio files sent to the `transcribe` tool and text prompts sent to the `chat` tool go directly to the secure Vinkius sandbox. Your raw data is never stored or used for training, keeping your intellectual property completely isolated.

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