togetherai_completion
Run a text completion with any Together AI model.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/togetherai-completion.md
What togetherai_completion does on UnClick
AI agents invoke togetherai_completion to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
stop | array | — | Stop sequences |
model | string | — | Model ID (e.g. mistralai/Mistral-7B-v0.1) |
top_k | number | — | Top-k sampling |
top_p | number | — | Top-p nucleus sampling |
prompt | string | Yes | Text prompt to complete |
api_key | string | Yes | Together AI API key |
max_tokens | number | — | Maximum tokens to generate |
temperature | number | — | Sampling temperature 0-2 |
Parameters from the server's own tool schema.
Why togetherai_completion is rated High
The tool invokes an external AI model (Together AI) to perform text completion, which is a form of code/logic execution. The open-ended nature ('any model') and parameter-dependent effects classify this as Execute rather than Read. While LLM completions are generally less destructive than shell execution, they can produce outputs that drive subsequent actions with significant side effects.
From the tool's definition Tool runs arbitrary text completion with "any Together AI model" - this executes code/models with effects determined by user input and model responses, fitting the Execute definition of triggering external operations whose effects depend on arguments.
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
The rule that runs togetherai_completion safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For togetherai_completion, this is the rule to start with:
togetherai_completion stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every togetherai_completion call is checked against it from then on.
Questions about togetherai_completion
Run a text completion with any Together AI model. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
togetherai_completion accepts 8 parameters: stop, model, top_k, top_p, prompt, api_key, max_tokens, temperature. Required: prompt, api_key. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for togetherai_completion: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.
togetherai_completion is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the togetherai_completion rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for togetherai_completion. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
togetherai_completion is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
Across the catalogue