Together AI MCP by usefulapi
Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints
Reviews
No review yet. Used Together AI MCP by usefulapi? Be the first to help others choose.What it does
Together AI MCP by usefulapi is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.
No capability identified yet from its description.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 1d ago (live check)Hosted endpoint
https://together-ai.usefulapi.io/mcpstreamable-http
In Claude Code: claude mcp add --transport http together-ai https://together-ai.usefulapi.io/mcp
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"together-ai": {
"url": "https://together-ai.usefulapi.io/mcp"
}
}
}Live check
Electra Index connected to the hosted endpoint 1d agoONLINE Together AI MCP by usefulapi answered an MCP connection on 15 Nov 2026 and introduced itself as together-ai-mcp 1.39.2 (MCP protocol 2025-06-18).
23 tools offered to AI assistants
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.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_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_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_list_fine_tunes· List fine-tuning jobs with status, base model, output model name and training settings. Together: GET /fine-tunes.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_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_batches· List batch inference jobs with status, progress, model and input/output/error file ids. Together: GET /batches.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_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_get_endpoint· Fetch one dedicated endpoint: state, model, hardware, autoscaling bounds and display name. Together: GET /endpoints/{endpointId}.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.
Show 11 more
together_list_evaluations· List LLM-as-a-judge evaluation jobs (classify, score, compare) with status, parameters and results once completed. Together: GET /evaluation.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_embeddings· Generate vector embeddings for one or more texts (billed per token). Together: POST /embeddings.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_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_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_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_cancel_batch· Cancel a batch job that has not finished. Together: POST /batches/{id}/cancel.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_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.
What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method
Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Version | 1.40.0 | DECLARED | SRC-001 Official MCP Registry | 13m ago |
| Hosted endpoint | https://together-ai.usefulapi.io/mcp | DECLARED | SRC-001 Official MCP Registry | 13m ago |
| Website | https://usefulapi.io/together-ai/ | DECLARED | SRC-001 Official MCP Registry | 13m ago |
| Local install (package) | no | DECLARED | SRC-001 Official MCP Registry | 13m ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 13m ago |
| Repository | https://github.com/m190/usefulapi-mcp | DECLARED | SRC-001 Official MCP Registry | 13m ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 13m ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 13m ago |
Change history
- VERSION16 Nov 20261.39.3 → 1.40.0
- VERSION16 Nov 20261.39.2 → 1.39.3
- VERSION14 Nov 20261.39.1 → 1.39.2
- VERSION13 Nov 20261.39.0 → 1.39.1
- VERSION13 Nov 20261.38.0 → 1.39.0
- VERSION11 Nov 20261.37.3 → 1.38.0
- VERSION11 Nov 20261.37.2 → 1.37.3
- VERSION10 Nov 20261.37.1 → 1.37.2
- VERSION10 Nov 20261.37.0 → 1.37.1
- VERSION10 Nov 20261.36.5 → 1.37.0
- VERSION07 Nov 20261.36.4 → 1.36.5
- VERSION07 Nov 20261.36.3 → 1.36.4
- VERSION07 Nov 20261.36.2 → 1.36.3
- VERSION06 Nov 20261.36.1 → 1.36.2
- VERSION06 Nov 20261.35.4 → 1.36.1
- VERSION06 Nov 20261.35.3 → 1.35.4
- VERSION05 Nov 20261.35.2 → 1.35.3
- VERSION05 Nov 20261.35.1 → 1.35.2
- VERSION03 Nov 20261.35.0 → 1.35.1
- VERSION03 Nov 20261.34.1 → 1.35.0
- VERSION03 Nov 20261.34.0 → 1.34.1
- VERSION02 Nov 20261.33.0 → 1.34.0
- VERSION31 Oct 20261.32.0 → 1.33.0
- VERSION31 Oct 20261.31.0 → 1.32.0
- VERSION31 Oct 20261.30.0 → 1.31.0
- VERSION31 Oct 20261.29.2 → 1.30.0
- VERSION30 Oct 20261.29.1 → 1.29.2
- VERSION30 Oct 20261.29.0 → 1.29.1
- VERSION29 Oct 20261.28.0 → 1.29.0
- VERSION29 Oct 20261.27.0 → 1.28.0
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is Together AI MCP by usefulapi still online?
Free alerts · no account▲ 0Do you run Together AI MCP by usefulapi? Know when it stops answering
For publishers · optionalIts hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.
Monitoring never changes a score or a rank.
Questions about Together AI MCP by usefulapi
How do I connect Together AI MCP by usefulapi?
Use the hosted endpoint https://together-ai.usefulapi.io/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
What tools does Together AI MCP by usefulapi offer?
When Electra Index connected on 15 Nov 2026, it listed 23 tools: together_whoami, together_list_models, together_list_files, together_get_file, together_list_fine_tunes, together_get_fine_tune, together_list_fine_tune_events, together_list_batches and more. The full list is in "Live check" above.
Is Together AI MCP by usefulapi online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 1d ago.