How to Use the Fireworks AI MCP in VS Code Copilot

Q: How do we roll out the Fireworks AI MCP Server to our team in VS Code Copilot?

Create a .vscode/mcp.json file at the root of your shared git repository. Once committed, any team member using VS Code Copilot (version 1.96+) will automatically load the Fireworks AI server tools.

Q: Can VS Code Copilot run local audio transcription via Fireworks AI?

Yes, the agent in VS Code Copilot uses the transcribe tool to process audio files stored in your workspace, converting them to text directly inside your active VS Code Copilot session using the Fireworks AI API.

Q: How does VS Code Copilot know which Fireworks AI models are active?

The VS Code Copilot agent runs the listmodels tool behind the scenes to fetch the latest list of available open-source models, allowing it to route prompts dynamically to Fireworks AI.

Q: Can we use this Fireworks AI server to generate vector embeddings for our team's codebase in VS Code Copilot?

Yes. The embed tool generates precise vector embeddings for your files via Fireworks AI, helping VS Code Copilot understand the semantic structure of your project.

Equip your entire team with high-speed open-source model inference and vector embedding tools directly inside VS Code Copilot using this Fireworks AI 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 Fireworks AI MCP to VS Code Copilot

Create your Vinkius account to connect Fireworks AI to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route VS Code Copilot requests to Fireworks AI models

Standardize your team's development environment. By adding this Fireworks AI MCP Server to your shared `.vscode/mcp.json` file, every developer gains access to the Fireworks AI `chat` and `completion` tools instantly inside VS Code Copilot. Your team can run code generation tasks against highly optimized open weights models hosted by Fireworks AI. It keeps your VS Code Copilot development flow fast and ensures everyone is working with the same model parameters.

Index team repositories using VS Code Copilot embeddings

Large codebases can overwhelm standard editor search. Let VS Code Copilot run the Fireworks AI `embed` tool to generate vector representations of your repository's files. This lets the VS Code Copilot agent perform highly accurate semantic searches across the entire project using Fireworks AI vectors. Developers can find obscure functions and understand complex dependencies without reading thousands of lines of code.

Transcribe specs and generate assets in VS Code Copilot

Turn voice recordings of sprint planning sessions into actionable code using this Fireworks AI MCP within VS Code Copilot. The agent uses the `transcribe` tool to convert audio specs into clean markdown files directly in your workspace. If you need quick visual assets for front-end mockups, the VS Code Copilot agent calls the Fireworks AI `image` tool to drop high-quality graphics straight into your project folders. It removes the friction of switching from VS Code Copilot to external design tools.

Setup guide

Set up Fireworks AI MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Fireworks AI MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Fireworks AI tools listed. Try asking: "List my recent Fireworks AI transactions" and Copilot will invoke them automatically.

.vscode/mcp.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 VS Code Copilot

Create a `.vscode/mcp.json` file at the root of your shared git repository. Once committed, any team member using VS Code Copilot (version 1.96+) will automatically load the Fireworks AI server tools.

Yes, the agent in VS Code Copilot uses the `transcribe` tool to process audio files stored in your workspace, converting them to text directly inside your active VS Code Copilot session using the Fireworks AI API.

The VS Code Copilot agent runs the `list_models` tool behind the scenes to fetch the latest list of available open-source models, allowing it to route prompts dynamically to Fireworks AI.

Yes. The `embed` tool generates precise vector embeddings for your files via Fireworks AI, helping VS Code Copilot understand the semantic structure of your project.

All prompt text and embeddings vectors are transmitted via secure TLS encryption directly to the Fireworks AI API. Vinkius hosts the connection in a zero-trust, ephemeral V8 isolate sandbox, guaranteeing that your VS Code Copilot data is never stored or used for training.

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