MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Together AI is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
23
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http together-ai-mcp https://together-ai.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# together_whoami, together_list_models, together_list_files and 20 more
Together AI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 334 servers
usefulapi334 servers
24 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http together-ai-mcp https://together-ai.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
23 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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.
No parameter schema on file.
List Together's models with type (chat, language, code, image, embedding, moderation, rerank), context length, organization, license and per-token pricing. Together: GET /models.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dedicated | boolean | no | Only return models that can run on dedicated endpoints. |
List uploaded data files (fine-tune, eval and batch-api inputs, plus job outputs) with size, type, purpose and validation status. Together: GET /files.
No parameter schema on 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}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_id | string | yes | The file id, e.g. file-abc123. |
List fine-tuning jobs with status, base model, output model name and training settings. Together: GET /fine-tunes.
No parameter schema on file.
Fetch one fine-tuning job: status, progress, hyperparameters, token counts, cost and the output model name. Together: GET /fine-tunes/{id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| fine_tune_id | string | yes | The job id, e.g. ft-abc123. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| fine_tune_id | string | yes | The job id, e.g. ft-abc123. |
List batch inference jobs with status, progress, model and input/output/error file ids. Together: GET /batches.
No parameter schema on file.
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}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| batch_id | string | yes | The batch job id. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | Filter by endpoint type. |
| usage_type | string | no | Filter by usage type. |
| mine | boolean | no | Only endpoints owned by the caller. |
Fetch one dedicated endpoint: state, model, hardware, autoscaling bounds and display name. Together: GET /endpoints/{endpointId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| endpoint_id | string | yes | The endpoint id, e.g. endpoint-d23901de-.... |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | no | Only hardware compatible with this model, with availability. |
List LLM-as-a-judge evaluation jobs (classify, score, compare) with status, parameters and results once completed. Together: GET /evaluation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Filter by status: pending, queued, running, completed, error, user_error. |
| limit | integer | no | Maximum number of jobs to return. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Model name, e.g. meta-llama/Llama-3.3-70B-Instruct-Turbo. |
| messages | array | yes | The conversation so far. |
| max_tokens | integer | no | Maximum tokens to generate. |
| temperature | number | no | — |
| top_p | number | no | — |
| top_k | integer | no | — |
| repetition_penalty | number | no | — |
| stop | array | no | Stop sequences. |
| seed | integer | no | Seed for reproducible sampling. |
| reasoning_effort | string | no | Reasoning effort for reasoning models that support it. |
Generate vector embeddings for one or more texts (billed per token). Together: POST /embeddings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Embedding model, e.g. BAAI/bge-large-en-v1.5. |
| input | yes | A text, or a list of texts, to embed. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Image model, e.g. black-forest-labs/FLUX.1-schnell. |
| prompt | string | yes | What to draw. |
| negative_prompt | string | no | What to steer away from. |
| width | integer | no | Width in pixels. |
| height | integer | no | Height in pixels. |
| n | integer | no | Number of images. |
| steps | integer | no | Number of generation steps. |
| seed | integer | no | — |
| guidance_scale | number | no | Prompt adherence; higher is more literal. |
| image_url | string | no | Input image URL, for models that support editing. |
| output_format | string | no | — |
| response_format | string | no | url (default here) or base64. base64 can be very large. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Base model to fine-tune. |
| training_file | string | yes | File id of an uploaded training file (purpose fine-tune). |
| validation_file | string | no | File id of an uploaded validation file. |
| suffix | string | no | Suffix for the fine-tuned model's name (max 64 chars). |
| n_epochs | integer | no | Passes over the training data. |
| n_checkpoints | integer | no | Intermediate checkpoints to save. |
| n_evals | integer | no | Evaluations on the validation set during training. |
| batch_size | no | Batch size, or 'max' (the default). | |
| learning_rate | number | no | — |
| warmup_ratio | number | no | — |
| max_seq_length | integer | no | — |
| from_checkpoint | string | no | Continue from a previous job: <job_id>, <output_model_name>, optionally with :<step>. |
| training_type | no | Full fine-tune or LoRA. Together defaults to LoRA when omitted. | |
| training_method | no | Supervised fine-tuning (sft, the default) or preference tuning (dpo). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| fine_tune_id | string | yes | The job id, e.g. ft-abc123. |
Start an asynchronous batch job over an uploaded JSONL input file (purpose batch-api), at a discount to real-time inference. Together: POST /batches.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| input_file_id | string | yes | File id of the uploaded JSONL request file. |
| endpoint | string | yes | The API each line of the input file is sent to. |
| model_id | string | no | Model to process the requests with. |
| completion_window | string | no | Time window for completion, e.g. 24h. |
| priority | integer | no | Processing priority. |
Cancel a batch job that has not finished. Together: POST /batches/{id}/cancel.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| batch_id | string | yes | The batch job id. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | The model to deploy. |
| hardware | string | yes | Hardware id, e.g. 1x_nvidia_a100_80gb_sxm. |
| autoscaling | object | yes | Replica bounds for autoscaling. |
| display_name | string | no | Human-readable name. |
| availability_zone | string | no | Availability zone, e.g. us-central-4b. |
| inactive_timeout | integer | no | Minutes of inactivity before auto-stop; 0 disables it. |
| disable_speculative_decoding | boolean | no | — |
| state | string | no | Initial state. Pass STOPPED to create without starting (and without billing). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| endpoint_id | string | yes | The endpoint id. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| endpoint_id | string | yes | The endpoint id. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Together AI or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.11.1.
1.11.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Together AI can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.