Together AI MCP by usefulapi MCP Server

by usefulapi Your server? Claim it

answering

Together AI MCP by usefulapi is answering right now. Last checked 6 min ago. It exposes 23 tools. Last commit 1 Nov 2026.

Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints.

Uptime history 33 days of history · worst day 99%

33 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

165 ms

Response time

average over 24h

Stars

last commit 1 Nov 2026

What changed 29

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 1 October 2026. No other catalogue keeps this.

31 Oct a tool changed version4 times that day

30 Oct a tool changed version2 times that day

29 Oct a tool changed version2 times that day

28 Oct a tool changed version2 times that day

27 Oct a tool changed version

25 Oct a tool changed version4 times that day

24 Oct a tool changed version3 times that day

23 Oct a tool changed version

22 Oct a tool changed version

20 Oct a tool changed version3 times that day

and 19 more, back to 1 October 2026

Together AI MCP by usefulapi missed one check this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add together-ai --transport http https://together-ai.usefulapi.io/mcp

Settings → Connectors → Add custom connector, then paste this address

https://together-ai.usefulapi.io/mcp

~/.codex/config.toml

[mcp_servers.together-ai]
url = "https://together-ai.usefulapi.io/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "together-ai": {
      "url": "https://together-ai.usefulapi.io/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "together-ai": {
      "type": "http",
      "url": "https://together-ai.usefulapi.io/mcp"
    }
  }
}

Available tools 23

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

together

together_cancel_batch

Cancel a batch job that has not finished. Together: POST /batches/{id}/cancel.

together_cancel_fine_tune

Cancel a running fine-tuning job. Cannot be resumed, but a new job can continue from its last checkpoint via from_checkpoint. Together: POST /fine-tunes/{id}/cancel.

together_chat_completion

Run a chat completion on a Together model (billed per token). Non-streaming. For a dedicated endpoint pass its `<project_slug>/<endpoint_slug>` as the model. Together: POST /chat/completions.

together_create_batch

Start an asynchronous batch job over an uploaded JSONL input file (purpose batch-api), at a discount to real-time inference. Together: POST /batches.

together_create_embeddings

Generate vector embeddings for one or more texts (billed per token). Together: POST /embeddings.

together_create_endpoint

Deploy a model on dedicated GPUs. The endpoint STARTS AUTOMATICALLY and bills per minute of uptime until stopped — set inactive_timeout to auto-stop it, and use together_list_hardware for valid hardware ids. Together: POST /endpoints.

together_create_fine_tune

Start a fine-tuning job on an uploaded training file (billed per token processed). Stop it with together_cancel_fine_tune. Together: POST /fine-tunes.

together_generate_image

Generate images from a prompt (billed per image/megapixel). Returns image URLs by default rather than base64, to keep responses small. Together: POST /images/generations.

together_get_batch

Fetch one batch job: status (VALIDATING, IN_PROGRESS, COMPLETED, FAILED, EXPIRED, CANCELLED), progress, and the output_file_id / error_file_id once done. Together: GET /batches/{id}.

together_get_endpoint

Fetch one dedicated endpoint: state, model, hardware, autoscaling bounds and display name. Together: GET /endpoints/{endpointId}.

together_get_file

Fetch one file's metadata, including its processing_status and validation_report (why a fine-tune training file was rejected). Together: GET /files/{id}.

together_get_fine_tune

Fetch one fine-tuning job: status, progress, hyperparameters, token counts, cost and the output model name. Together: GET /fine-tunes/{id}.

together_list_batches

List batch inference jobs with status, progress, model and input/output/error file ids. Together: GET /batches.

together_list_endpoints

List endpoints with model, owner and state (PENDING, STARTING, STARTED, STOPPING, STOPPED, ERROR). Use mine=true and type=dedicated to see what is running on your account and billing by the minute. Together: GET /endpoints.

together_list_evaluations

List LLM-as-a-judge evaluation jobs (classify, score, compare) with status, parameters and results once completed. Together: GET /evaluation.

together_list_files

List uploaded data files (fine-tune, eval and batch-api inputs, plus job outputs) with size, type, purpose and validation status. Together: GET /files.

together_list_fine_tune_events

List the event log of one fine-tuning job (queued, started, checkpoint saved, epoch completed, errors). The first place to look when a job failed. Together: GET /fine-tunes/{id}/events.

together_list_fine_tunes

List fine-tuning jobs with status, base model, output model name and training settings. Together: GET /fine-tunes.

together_list_hardware

List hardware configurations for dedicated endpoints with GPU type/count/memory and price in cents per minute. Pass a model to get only compatible configurations with live availability. Together: GET /hardware.

together_list_models

List Together's models with type (chat, language, code, image, embedding, moderation, rerank), context length, organization, license and per-token pricing. Together: GET /models.

together_start_endpoint

Start a stopped dedicated endpoint. It bills per minute of uptime until stopped. Reversible with together_stop_endpoint. Together: PATCH /endpoints/{endpointId} with state=STARTED.

together_stop_endpoint

Stop a running dedicated endpoint, which stops its per-minute billing. Requests to it fail until it is started again. Together: PATCH /endpoints/{endpointId} with state=STOPPED.

together_whoami

Identify the API key: its organization, project and project slug. The project slug forms the `<project_slug>/<endpoint_slug>` model name for dedicated-endpoint inference. A cheap way to confirm the key works. Together: GET /whoami.

Endpoints

URL	Transport	State	Latency	Checked
https://together-ai.usefulapi.io/mcp	streamable-http	answering	279 ms	6 min ago

Alternatives to Together AI MCP by usefulapi

same job, measured the same way

gigachat-mcp

by theyahia

MCP server for GigaChat — AI chat, embeddings, image generation (Russia)

58 installs/wk local only

GPT Chat

by codechap

MCP server for the OpenAI ChatGPT API — chat, vision, and embeddings

local only

Grok Chat

by codechap

MCP server for the xAI Grok API — chat, vision, search, and embeddings

local only

Mistral MCP by usefulapi

by usefulapi

Manage your Mistral platform — models, files, batch jobs, agents and RAG document libraries.

15 tools answering

IBM watsonx.ai Granite

by nirholas

IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.

77 installs/wk local only

MCP Openai

by acedatacloud

MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud

2 290 installs/wk answering

deAPI MCP Server

by deapi-ai

35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI

answering

Agent Data Tools: AI

by nutshell2000

25 tools: LLM chat, summaries, translation, embeddings, speech, images. 25 free calls.

25 tools answering

Together AI MCP by usefulapi — questions

Answers built from our own checks of this server.

What can Together AI MCP by usefulapi do?

It exposes 23 tools, read directly from the server on our last check. Among them: together_cancel_batch, together_cancel_fine_tune, together_chat_completion, together_create_batch, together_create_embeddings, together_create_endpoint and 17 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Together AI MCP by usefulapi working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 165 ms. The bar chart above shows every period we have measured.

How do I connect Together AI MCP by usefulapi?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Together AI MCP by usefulapi need an API key?

No. Together AI MCP by usefulapi completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 23 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Together AI MCP by usefulapi?

It answers our handshake in 165 ms on average, which is faster than 80% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Together AI MCP by usefulapi open source?

The code is open source: it is published under the MIT licence, written in JavaScript, 1 stars on GitHub and 1 open issue. The licence covers the code in the repository, not the hosted service at together-ai.usefulapi.io, which runs on its operator's own terms.