io.usefulapi/together-ai
REMOTE · TOGETHER-AI.USEFULAPI.IO · SCANNED OCT 4
Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security89
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability81
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 2082 tokens (~90/item across 23 items; 23 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 85% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 23 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
How do I install the io.usefulapi/together-ai MCP server?
io.usefulapi/together-ai is a hosted endpoint at https://together-ai.usefulapi.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · together-ai.usefulapi.io
claude mcp add --transport http io-usefulapi-together-ai 'https://together-ai.usefulapi.io/mcp'
{
"mcpServers": {
"io-usefulapi-together-ai": {
"url": "https://together-ai.usefulapi.io/mcp"
}
}
} {
"servers": {
"io-usefulapi-together-ai": {
"type": "http",
"url": "https://together-ai.usefulapi.io/mcp"
}
}
} [mcp_servers.io-usefulapi-together-ai] url = "https://together-ai.usefulapi.io/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"io-usefulapi-together-ai": {
"type": "remote",
"url": "https://together-ai.usefulapi.io/mcp",
"enabled": true
}
}
} openclaw mcp add io-usefulapi-together-ai --url 'https://together-ai.usefulapi.io/mcp' --transport streamable-http
mcp_servers:
io-usefulapi-together-ai:
url: "https://together-ai.usefulapi.io/mcp" {
"McpServers": {
"io-usefulapi-together-ai": {
"Transport": "http",
"Url": "https://together-ai.usefulapi.io/mcp"
}
}
} assistant mcp add io-usefulapi-together-ai -t streamable-http -u 'https://together-ai.usefulapi.io/mcp'
{
"mcpServers": {
"io-usefulapi-together-ai": {
"type": "http",
"url": "https://together-ai.usefulapi.io/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Oct 26 0
- Server version: 1.3.0 → 1.5.1 functional
- 1 Oct 26 +5
- HTTPS: unverified → pass ▲ security
- Stability: unverified → 0.03 ▲ functional
- Server version: 1.0.0 → 1.3.0 functional
- 30 Sept 26 +54
- Authorization: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- First check of Judged manipulation: pass security
- First check of Authorization: partial security
- MCP protocol: unverified → fail ▼ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Schema quality: excellent functional
- First check of Tool coverage: 85 functional
- First check of Destructive annotations: 100 functional
- First check of Schema quality: pass functional
- 29 Sept 26 18
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Oct 2026 · Probed https://together-ai.usefulapi.io/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=usefulapi.io | CN=WE1,O=Google Trust Services,C=US | 13 Sept 2026 | 12 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | d9be3287b0fde9630e825ba1f79bff3f |
| SANs: usefulapi.io, *.usefulapi.io | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of together-ai.usefulapi.io. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| io. | present | 57355 | 8 | Verified |
| usefulapi.io. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer realm="OAuth", resource_metadata="https://together-ai.usefulapi.io/.well-known/oauth-protected-resource/mcp"
Bearer realm="OAuth", resource_metadata="https://together-ai.usefulapi.io/.well-known/oauth-protected-resource/mcp"Protected resource metadata
| Document | https://together-ai.usefulapi.io/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://together-ai.usefulapi.io/mcp |
| Authorisation server | https://together-ai.usefulapi.io |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://together-ai.usefulapi.io/mcp | Verified | 200 | |
| http (plaintext) | http://together-ai.usefulapi.io/mcp | HTTPS enforced | 301 | https://together-ai.usefulapi.io/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
together_cancel_batch Cancel a batch job ~41
Cancel a batch job that has not finished. Together: POST /batches/{id}/cancel.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | The batch job id. |
No output schema declared.
No examples provided.
together_cancel_fine_tune Cancel a fine-tuning job ~71
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.
| Name | Type | Req | Description |
|---|---|---|---|
| fine_tune_id | string | yes | The job id, e.g. ft-abc123. |
No output schema declared.
No examples provided.
together_chat_completion Chat completion ~177
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.
| Name | Type | Req | Description |
|---|---|---|---|
| max_tokens | integer | – | Maximum tokens to generate. |
| messages | array | yes | The conversation so far. |
| model | string | yes | Model name, e.g. meta-llama/Llama-3.3-70B-Instruct-Turbo. |
| reasoning_effort | string | – | Reasoning effort for reasoning models that support it. |
| repetition_penalty | number | – | – |
| seed | integer | – | Seed for reproducible sampling. |
| stop | array | – | Stop sequences. |
| temperature | number | – | – |
| top_k | integer | – | – |
| top_p | number | – | – |
No output schema declared.
No examples provided.
together_create_batch Create a batch job ~119
Start an asynchronous batch job over an uploaded JSONL input file (purpose batch-api), at a discount to real-time inference. Together: POST /batches.
| Name | Type | Req | Description |
|---|---|---|---|
| completion_window | string | – | Time window for completion, e.g. 24h. |
| endpoint | string | yes | The API each line of the input file is sent to. |
| input_file_id | string | yes | File id of the uploaded JSONL request file. |
| model_id | string | – | Model to process the requests with. |
| priority | integer | – | Processing priority. |
No output schema declared.
No examples provided.
together_create_embeddings Create embeddings ~71
Generate vector embeddings for one or more texts (billed per token). Together: POST /embeddings.
| Name | Type | Req | Description |
|---|---|---|---|
| input | – | yes | A text, or a list of texts, to embed. |
| model | string | yes | Embedding model, e.g. BAAI/bge-large-en-v1.5. |
No output schema declared.
No examples provided.
together_create_endpoint Create a dedicated endpoint ~188
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.
| Name | Type | Req | Description |
|---|---|---|---|
| autoscaling | object | yes | Replica bounds for autoscaling. |
| availability_zone | string | – | Availability zone, e.g. us-central-4b. |
| disable_speculative_decoding | boolean | – | – |
| display_name | string | – | Human-readable name. |
| hardware | string | yes | Hardware id, e.g. 1x_nvidia_a100_80gb_sxm. |
| inactive_timeout | integer | – | Minutes of inactivity before auto-stop; 0 disables it. |
| model | string | yes | The model to deploy. |
| state | string | – | Initial state. Pass STOPPED to create without starting (and without billing). |
No output schema declared.
No examples provided.
together_create_fine_tune Create a fine-tuning job ~277
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.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_size | – | – | Batch size, or 'max' (the default). |
| from_checkpoint | string | – | Continue from a previous job: <job_id>, <output_model_name>, optionally with :<step>. |
| learning_rate | number | – | – |
| max_seq_length | integer | – | – |
| model | string | yes | Base model to fine-tune. |
| n_checkpoints | integer | – | Intermediate checkpoints to save. |
| n_epochs | integer | – | Passes over the training data. |
| n_evals | integer | – | Evaluations on the validation set during training. |
| suffix | string | – | Suffix for the fine-tuned model's name (max 64 chars). |
| training_file | string | yes | File id of an uploaded training file (purpose fine-tune). |
| training_method | – | – | Supervised fine-tuning (sft, the default) or preference tuning (dpo). |
| training_type | – | – | Full fine-tune or LoRA. Together defaults to LoRA when omitted. |
| validation_file | string | – | File id of an uploaded validation file. |
| warmup_ratio | number | – | – |
No output schema declared.
No examples provided.
together_generate_image Generate an image ~208
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.
| Name | Type | Req | Description |
|---|---|---|---|
| guidance_scale | number | – | Prompt adherence; higher is more literal. |
| height | integer | – | Height in pixels. |
| image_url | string | – | Input image URL, for models that support editing. |
| model | string | yes | Image model, e.g. black-forest-labs/FLUX.1-schnell. |
| n | integer | – | Number of images. |
| negative_prompt | string | – | What to steer away from. |
| output_format | string | – | – |
| prompt | string | yes | What to draw. |
| response_format | string | – | url (default here) or base64. base64 can be very large. |
| seed | integer | – | – |
| steps | integer | – | Number of generation steps. |
| width | integer | – | Width in pixels. |
No output schema declared.
No examples provided.
together_get_batch Get one batch job ~68
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}.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | The batch job id. |
No output schema declared.
No examples provided.
together_get_endpoint Get one endpoint ~58
Fetch one dedicated endpoint: state, model, hardware, autoscaling bounds and display name. Together: GET /endpoints/{endpointId}.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | yes | The endpoint id, e.g. endpoint-d23901de-.... |
No output schema declared.
No examples provided.
together_get_file Get one file ~60
Fetch one file's metadata, including its processing_status and validation_report (why a fine-tune training file was rejected). Together: GET /files/{id}.
| Name | Type | Req | Description |
|---|---|---|---|
| file_id | string | yes | The file id, e.g. file-abc123. |
No output schema declared.
No examples provided.
together_get_fine_tune Get one fine-tuning job ~67
Fetch one fine-tuning job: status, progress, hyperparameters, token counts, cost and the output model name. Together: GET /fine-tunes/{id}.
| Name | Type | Req | Description |
|---|---|---|---|
| fine_tune_id | string | yes | The job id, e.g. ft-abc123. |
No output schema declared.
No examples provided.
together_list_batches List batch jobs ~33
List batch inference jobs with status, progress, model and input/output/error file ids. Together: GET /batches.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
together_list_endpoints List endpoints ~101
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.
| Name | Type | Req | Description |
|---|---|---|---|
| mine | boolean | – | Only endpoints owned by the caller. |
| type | string | – | Filter by endpoint type. |
| usage_type | string | – | Filter by usage type. |
No output schema declared.
No examples provided.
together_list_evaluations List evaluation jobs ~79
List LLM-as-a-judge evaluation jobs (classify, score, compare) with status, parameters and results once completed. Together: GET /evaluation.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of jobs to return. |
| status | string | – | Filter by status: pending, queued, running, completed, error, user_error. |
No output schema declared.
No examples provided.
together_list_files List files ~44
List uploaded data files (fine-tune, eval and batch-api inputs, plus job outputs) with size, type, purpose and validation status. Together: GET /files.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
together_list_fine_tune_events List a fine-tuning job's events ~79
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.
| Name | Type | Req | Description |
|---|---|---|---|
| fine_tune_id | string | yes | The job id, e.g. ft-abc123. |
No output schema declared.
No examples provided.
together_list_fine_tunes List fine-tuning jobs ~38
List fine-tuning jobs with status, base model, output model name and training settings. Together: GET /fine-tunes.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
together_list_hardware List hardware ~63
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.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | – | Only hardware compatible with this model, with availability. |
No output schema declared.
No examples provided.
together_list_models List models ~64
List Together's models with type (chat, language, code, image, embedding, moderation, rerank), context length, organization, license and per-token pricing. Together: GET /models.
| Name | Type | Req | Description |
|---|---|---|---|
| dedicated | boolean | – | Only return models that can run on dedicated endpoints. |
No output schema declared.
No examples provided.
together_start_endpoint Start a dedicated endpoint ~58
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.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | yes | The endpoint id. |
No output schema declared.
No examples provided.
together_stop_endpoint Stop a dedicated endpoint ~59
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.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | yes | The endpoint id. |
No output schema declared.
No examples provided.
together_whoami Who am I ~59
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the io.usefulapi/together-ai MCP server?
io.usefulapi/together-ai is an MCP server listed in the public MCP registry as io.usefulapi/together-ai. Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints. This page covers its hosted endpoint (https://together-ai.usefulapi.io/mcp).
Is the io.usefulapi/together-ai MCP server safe to use?
io.usefulapi/together-ai scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.usefulapi/together-ai MCP server expose?
io.usefulapi/together-ai exposes 23 tools: together_whoami, together_list_models, together_list_files, together_get_file, together_list_fine_tunes, and 18 more. Their descriptions and schemas cost roughly 2,082 tokens of context every time the server is loaded.
Does the io.usefulapi/together-ai MCP server require authentication?
Yes. io.usefulapi/together-ai asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the io.usefulapi/together-ai MCP server still maintained?
io.usefulapi/together-ai is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.