How to Use the Fireworks AI MCP in Claude Code

Q: How do I add the Fireworks AI MCP server to Claude Code?

Run the command claude mcp add --transport http fireworks-ai -- in your terminal. This registers the MCP server to your local configuration and makes all six tools instantly available in your CLI.

Q: Can I run semantic codebase searches using Claude Code?

Yes. The embed tool generates vector representations of your local files. Claude Code uses these vectors to perform fast semantic searches, letting you locate bugs across your repository directly from the terminal.

Q: Is my terminal data safe when using Fireworks AI with Claude Code?

Yes. All terminal inputs sent to chat and audio files processed by transcribe go through this MCP server to a zero-trust V8 isolate sandbox. Your raw text and audio data are never stored, keeping your command-line operations fully secure.

Run ultra-fast Fireworks AI model inference, embeddings, and transcriptions directly from your Claude Code terminal.

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 Claude Code

Create your Vinkius account to connect Fireworks AI to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless model discovery for Claude Code

The `list_models` tool queries the Fireworks AI registry directly from your command-line interface. When running automated scripts, Claude Code uses this MCP server to check which open-weights models are online and ready to accept inference requests. This enables dynamic fallback routing in your terminal workflows. If a specific model is offline, your CLI agent automatically selects an alternative from the returned list without crashing your build pipeline.

Fast pipeline execution via this MCP Server

The `chat` tool processes high-speed chat completions directly within your terminal session or CI/CD pipelines. Claude Code runs this tool to analyze logs, generate patch files, and automate code reviews at a fraction of the cost of standard APIs. To handle non-chat text generation, the `completion` tool executes raw prompts without chat template overhead. This is perfect for terminal-based automation where you need to pipe raw text outputs directly into other shell utilities.

Terminal-based asset generation and transcription

The `image` tool lets you generate visual assets directly from a terminal prompt without opening a web browser. Claude Code calls the endpoint, downloads the generated image, and saves it to your specified path in your current directory. For automated audio processing, the `transcribe` tool converts voice recordings into structured text files. Meanwhile, the `embed` tool generates vector embeddings of your files, enabling you to build powerful command-line semantic search tools.

Setup guide

Set up Fireworks AI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see fireworks-ai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Fireworks AI transactions." It will automatically discover and invoke the available Fireworks AI tools.

Terminal

claude mcp add --transport http fireworks-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "fireworks-ai-mcp": {
      "type": "url",
      "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 Claude Code

Run the command `claude mcp add --transport http fireworks-ai -- ` in your terminal. This registers the MCP server to your local configuration and makes all six tools instantly available in your CLI.

Yes. You can pipe text directly to Claude Code and have it run the `completion` tool. The agent executes the prompt using high-speed open-source models and outputs the raw text back to your shell.

When you command the CLI agent to build an image, it calls the `image` tool. The server processes the request and saves the output file directly to your local file system.

Yes. The `embed` tool generates vector representations of your local files. Claude Code uses these vectors to perform fast semantic searches, letting you locate bugs across your repository directly from the terminal.

Yes. All terminal inputs sent to `chat` and audio files processed by `transcribe` go through this MCP server to a zero-trust V8 isolate sandbox. Your raw text and audio data are never stored, keeping your command-line operations fully secure.

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