electrical_services

Together AI MCP Server — Hosted Ai Integration

MCP Server language Hosted language Public

Run open-source LLMs, generate embeddings, create images, and fine-tune models using Together AI's inference platform.

@aerostack verified

• v0.1.0 • MIT • Updated Jun 28, 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": {
    "together-ai": {
      "url": "https://mcp.aerostack.dev/s/aerostack/mcp-together-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:

+7 more

Natural Language Prompt

“Use the _ping tool to verify together 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-together-ai — Together AI MCP Server

Run open-source LLMs, generate embeddings, create images, and fine-tune models using Together AI's inference platform.

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

What You Can Do

This MCP server gives AI agents access to Together AI via 12 tools. Connect it to any Aerostack workspace and your agents can interact with Together AI directly.

Available Tools

Tool	Description
`chat`	Send messages to any Together AI chat model (Llama, Mistral, Qwen, etc.) and receive a response. OpenAI-compatible interface
`complete`	Text completion (non-chat) for any Together AI base model. Send a prompt and receive a completion
`embed`	Generate text embeddings for semantic search and similarity using Together AI embedding models
`generate_image`	Generate images from text prompts using Together AI image models like FLUX
`list_models`	List all available Together AI models with type, pricing, and context length information
`get_model`	Get detailed information about a specific Together AI model by its ID
`upload_file`	Upload a file to Together AI for use in fine-tuning jobs. Pass content as base64
`list_files`	List all uploaded files in your Together AI account
`delete_file`	Delete an uploaded file from your Together AI account
`create_fine_tuning_job`	Start a fine-tuning job to train a custom model on Together AI with your data
`list_fine_tuning_jobs`	List all fine-tuning jobs in your Together AI account
`get_fine_tuning_job`	Get the current status and details of a specific fine-tuning job

Configuration

Variable	Required	Description
`TOGETHER_API_KEY`	Yes	Together AI API key from https://api.together.xyz/settings/api-keys

Quick Start

Add to Aerostack Workspace

Go to aerostack.dev → Your Project → MCPs
Search for "Together AI" and click Add to Workspace

Add the following secrets under Project → Secrets:

TOGETHER_API_KEY

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

Direct API Call

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

License

MIT

terminal Tools (13)

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

terminal

_ping #1

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

terminal

chat #2

Send messages to any Together AI chat model (Llama, Mistral, Qwen, etc.) and receive a response. OpenAI-compatible interface

terminal

complete #3

Text completion (non-chat) for any Together AI base model. Send a prompt and receive a completion

terminal

embed #4

Generate text embeddings for semantic search and similarity using Together AI embedding models

terminal

generate_image #5

Generate images from text prompts using Together AI image models like FLUX

terminal

list_models #6

List all available Together AI models with type, pricing, and context length information

terminal

get_model #7

Get detailed information about a specific Together AI model by its ID

terminal

upload_file #8

Upload a file to Together AI for use in fine-tuning jobs. Pass content as base64

terminal

list_files #9

List all uploaded files in your Together AI account

terminal

delete_file #10

Delete an uploaded file from your Together AI account

terminal

create_fine_tuning_job #11

Start a fine-tuning job to train a custom model on Together AI with your data

terminal

list_fine_tuning_jobs #12

List all fine-tuning jobs in your Together AI account

terminal

get_fine_tuning_job #13

Get the current status and details of a specific fine-tuning job

Details

upgrade Version 0.1.0

gavel License MIT

wifi Transport streamable-http

lock Access Public

category Category AI

terminal Tools 13

language Live Endpoint

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

Sub-50ms globally · Zero cold start

Publisher

@aerostack verified

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

Frequently asked questions

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

The Together AI MCP server is hosted on Aerostack and exposes these tools to your AI agent: `_ping`, `chat`, `complete`, `embed`, `generate_image`. 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 Together 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 Together 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 Together 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 Together AI MCP server in Claude Desktop? +

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

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

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

Does Together AI MCP require authentication? +

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

Together AI MCP Server — Hosted Ai Integration

description Overview

mcp-together-ai — Together AI MCP Server

What You Can Do

Available Tools

Configuration

Quick Start

Add to Aerostack Workspace

Direct API Call

License

terminal Tools (13)

Details

Publisher

Tags

More in AI

Canva Design Platform

Intercom Messaging

Anthropic

Vercel Deployments

Gmail

Mailchimp

Frequently asked questions