Aerostack
Aerostack
electrical_services

Fireworks AI MCP Server — Hosted Ai Integration

MCP Server language Hosted language Public

Fast LLM inference via Fireworks AI — generate text, run chat completions, and access fine-tuned models at speed.

aerostack @aerostack verified
• v0.1.0 • MIT • Updated Jun 27, 2026
add_circleAdd to Workspace
robot_2

Use with AI AssistantsMCP

Connect Claude, Cursor, or any MCP-compatible client — then call tools directly

① Add This MCP Server

Paste into your AI client config — then all its tools are available instantly.

.claude/mcp.json
{
  "mcpServers": {
    "fireworks-ai": {
      "url": "https://mcp.aerostack.dev/s/aerostack/mcp-fireworks-ai",
      "headers": {
        "Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
      }
    }
  }
}

Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.

② Call a Tool

Ask your AI assistant to call a specific tool, or send raw JSON-RPC:

Natural Language Prompt

“Use the _ping tool to verify fireworks ai credentials by calling a lightweight read endpoint. used internally by aerostack to validate credentials”

Using a Workspace?

Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.

add_circleAdd to Workspace

description Overview

mcp-fireworks-ai — Fireworks AI MCP Server

Fast LLM inference via Fireworks AI — generate text, run chat completions, and access fine-tuned models at speed.

Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-fireworks-ai

What You Can Do

This MCP server gives AI agents access to Fireworks AI via 5 tools. Connect it to any Aerostack workspace and your agents can interact with Fireworks AI directly.

Available Tools

Tool Description
chat_completion Fast chat completion using Fireworks AI. Supports Llama, Mixtral, and other open-source models with OpenAI-compatible API. Default model: llama-v3p1-8b-instruct.
text_completion Raw text completion using Fireworks AI. Continues the provided prompt without chat formatting.
create_embedding Generate text embeddings using Fireworks AI nomic-embed-text-v1.5. Returns dense vectors for semantic search, clustering, and similarity.
list_models List all available models on Fireworks AI including chat, completion, embedding, and image generation models.
image_generation Generate images using Stable Diffusion XL on Fireworks AI. Returns image URLs.

Configuration

Variable Required Description
FIREWORKS_API_KEY Yes Your FIREWORKS API KEY from the service's developer settings

Quick Start

Add to Aerostack Workspace
  1. Go to aerostack.dev → Your Project → MCPs
  2. Search for "Fireworks AI" and click Add to Workspace

Add the following secrets under Project → Secrets:

  • FIREWORKS_API_KEY

Once added, every AI agent in your workspace can use Fireworks AI tools automatically.

Direct API Call
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-fireworks-ai \
  -H 'Content-Type: application/json' \
  -H 'X-Mcp-Secret-FIREWORKS-API-KEY: your-fireworks-api-key' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"chat_completion","arguments":{}}}'

License

MIT

terminal Tools (6)

Available tools on this MCP server. Each tool can be called directly from any AI agent.

terminal
_ping #1

Verify Fireworks AI credentials by calling a lightweight read endpoint. Used internally by Aerostack to validate credentials.

terminal
chat_completion #2

Fast chat completion using Fireworks AI. Supports Llama, Mixtral, and other open-source models with OpenAI-compatible API. Default model: llama-v3p1-8b-instruct.

terminal
text_completion #3

Raw text completion using Fireworks AI. Continues the provided prompt without chat formatting.

terminal
create_embedding #4

Generate text embeddings using Fireworks AI nomic-embed-text-v1.5. Returns dense vectors for semantic search, clustering, and similarity.

terminal
list_models #5

List all available models on Fireworks AI including chat, completion, embedding, and image generation models.

terminal
image_generation #6

Generate images using Stable Diffusion XL on Fireworks AI. Returns image URLs.

Details

upgrade Version 0.1.0
gavel License MIT
wifi Transport streamable-http
lock Access Public
category Category AI
terminal Tools 6

language Live Endpoint

https://mcp.aerostack.dev/s/aerostack/mcp-fireworks-ai

Sub-50ms globally · Zero cold start

Publisher

aerostack
@aerostack verified

Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.

Tags

fireworks llm inference generative-ai language-models
Browse more servers

More in AI

Browse AI MCPs →
hub

Canva Design Platform

by @aerostack

Design creation, AI generation, editing, export, assets, brand kits, folders via Canva's official MCP

ai
star 0
hub

Intercom Messaging

by @aerostack

Conversations, contacts, tickets, articles via Intercom's official MCP

ai
star 0
hub

Anthropic

by @aerostack

Call Claude models directly — run AI conversations, tool-use chains, batch jobs, and model comparisons from any agent.

ai
star 0
hub

Vercel Deployments

by @aerostack

Deployments, projects, domains, env vars, logs via Vercel's official MCP

ai
star 0
hub

Gmail

by @aerostack

Read, send, and search Gmail messages — manage labels, drafts, and attachments with full inbox control.

ai
star 0
hub

Mailchimp

by @aerostack

Manage audiences, campaigns, and subscriber tags in Mailchimp — automate your email marketing with AI.

ai
star 0

Frequently asked questions

What is the Fireworks AI MCP server and what can it do? +

The Fireworks AI MCP server is hosted on Aerostack and exposes these tools to your AI agent: `_ping`, `chat_completion`, `text_completion`, `create_embedding`, `list_models`. You get one hosted URL — no self-hosting — that works from Claude, Cursor, ChatGPT, Gemini, VS Code, or any MCP-compatible client, and you can share it with your team or combine it with other MCP servers in a workspace.

Is the Fireworks AI MCP server hosted, or do I have to run it myself? +

It's hosted on Aerostack's edge infrastructure — you don't deploy or maintain anything. Add it to a workspace and you get one authenticated URL, with secrets encrypted, that any AI agent or editor can connect to. Use it solo or share the same URL across your whole team.

Which AI agents and editors can use the Fireworks AI MCP server? +

Any MCP client: Claude and Claude Code, Cursor, ChatGPT, Gemini, Windsurf, Cline, VS Code, and custom agents. Because it's one hosted URL, the same Fireworks AI MCP server works everywhere — and you can compose it with other MCP servers, skills, and functions behind a single workspace URL.

How do I install the Fireworks AI MCP server in Claude Desktop? +

Add the following to your Claude Desktop config (`claude_desktop_config.json`): ```json { "mcpServers": { "@aerostack/mcp-fireworks-ai": { "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-fireworks-ai"] } } } ``` Then restart Claude Desktop and the tools will appear automatically.

How do I use the Fireworks AI MCP server in Cursor? +

In Cursor, open **Settings → MCP** and add: ```json { "name": "@aerostack/mcp-fireworks-ai", "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-fireworks-ai"] } ``` Save and reload Cursor. The MCP tools will be available in Agent mode.

Does Fireworks AI MCP require authentication? +

Yes. Fireworks AI requires authentication. Check the MCP's documentation for the required credentials.