# togetherai_chat_completion

Run a chat completion with any Together AI model. Supports Llama, Mistral, Qwen, and 100+ open-source models.

Agent View of the PolicyLayer registry record for `togetherai_chat_completion`. HTML page: https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/togetherai-chat-completion

## Facts

- Tool: `togetherai_chat_completion`
- Server: UnClick (`@unclick/mcp-server`) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Install: `npx -y @unclick/mcp-server`
- Homepage: https://github.com/malamutemayhem/unclick-agent-native-endpoints.git
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 8 (3 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `stop` | array | no | Stop sequences |
| `model` | string | yes | Model ID (e.g. meta-llama/Llama-3-8b-chat-hf). Use togetherai_list_models to browse. |
| `top_k` | number | no | Top-k sampling |
| `top_p` | number | no | Top-p nucleus sampling |
| `api_key` | string | yes | Together AI API key |
| `messages` | array | yes | Array of {role, content} message objects |
| `max_tokens` | number | no | Maximum tokens to generate |
| `temperature` | number | no | Sampling temperature 0-2 (default 0.7) |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "togetherai_chat_completion",
    "arguments": {
      "model": "<model>",
      "api_key": "<api_key>",
      "messages": []
    }
  }
}
```

## Why togetherai_chat_completion is rated High

This tool executes code/operations by invoking third-party AI models whose behavior depends entirely on the input arguments (prompts). An AI agent could use it to run arbitrary inference operations, generate malicious content, or chain outputs as inputs to other destructive tools.

From the tool's own definition: "The tool description explicitly states 'Run a chat completion with any Together AI model' - the verb 'Run' combined with 'any' model indicates execution of arbitrary operations."

Risk signals: Handles credentials or secrets (api_key)

## Use case

AI agents invoke togetherai_chat_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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches UnClick:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "togetherai_chat_completion": {
      "limits": [
        {
          "counter": "togetherai_chat_completion_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on UnClick (1661)

- `delete_todo` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/delete-todo.md
- `email_delete` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/email-delete.md
- `file_sync_prune` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/file-sync-prune.md
- `pinecone_delete_vectors` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/pinecone-delete-vectors.md
- `telegram_manage_chat` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/telegram-manage-chat.md
- `upstash_redis_del` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/upstash-redis-del.md
- `vault_action` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/vault-action.md
- `vercel_delete_env` — Destructive — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/vercel-delete-env.md
- `ackermann` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/ackermann.md
- `anthropic_create_message` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/anthropic-create-message.md
- `avl_tree` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/avl-tree.md
- `baby_giant_step` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/baby-giant-step.md
- `bellman_ford` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/bellman-ford.md
- `bezier_curve` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/bezier-curve.md
- `bitmask_ops` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/bitmask-ops.md
- `bitwise_calc` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/bitwise-calc.md
- `bloom_filter` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/bloom-filter.md
- `bluesky_action` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/bluesky-action.md
- `burrows_wheeler` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/burrows-wheeler.md
- `cartesian_tree` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/cartesian-tree.md
- `chromatic_number` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/chromatic-number.md
- `circleci_trigger_pipeline` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/circleci-trigger-pipeline.md
- `cohere_chat` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/cohere-chat.md
- `cohere_classify` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/cohere-classify.md
- `cohere_generate` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/cohere-generate.md
- `commonsensepass_check` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/commonsensepass-check.md
- `complex_calc` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/complex-calc.md
- `compliancepass_run` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/compliancepass-run.md
- `convex_hull_3d` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/convex-hull-3d.md
- `convolution` — Execute — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server/convolution.md
- …and 1631 more: https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-malamutemayhem-unclick-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-malamutemayhem-unclick-mcp-server