KosmoKrator

ai

Together AI MCP Integration for Vercel AI SDK

Connect Together AI to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

7 functions 6 read 1 write API key auth
Submit Together AI feedback View package source

Connect Together AI to Vercel AI SDK

Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.

Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with --write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.

Together AI MCP Config for Vercel AI SDK

Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.

{
  "mcpServers": {
    "kosmokrator-together-ai": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=together-ai",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=together-ai --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Together AI instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Together AI Tools Visible to Vercel AI SDK

Vercel AI SDK sees stable MCP tool names generated from the Together AI integration catalog.

MCP toolSource functionTypeDescription
integration__together_ai__togetherai_list_models together-ai.togetherai_list_models Read List all available AI models on Together AI, including open-source and fine-tuned models. Returns model IDs, types, pricing, and capabilities.
integration__together_ai__togetherai_create_completion together-ai.togetherai_create_completion Write Create a chat completion using a Together AI model. Send a conversation with messages and receive a generated response. Supports models like Llama, Mixtral, Qwen, DBRX, and more.
integration__together_ai__togetherai_list_fine_tunes together-ai.togetherai_list_fine_tunes Read List all fine-tuning jobs on Together AI. Returns job IDs, status, base model, training file, and creation timestamps.
integration__together_ai__togetherai_get_fine_tune together-ai.togetherai_get_fine_tune Read Get details of a specific fine-tuning job on Together AI. Returns status, training progress, hyperparameters, and the output model ID once complete.
integration__together_ai__togetherai_list_files together-ai.togetherai_list_files Read List all files uploaded to Together AI. Returns file IDs, filenames, sizes, and purposes (e.g. fine-tune training data, results).
integration__together_ai__togetherai_get_file together-ai.togetherai_get_file Read Get details of a specific file on Together AI. Returns file metadata including name, size, purpose, and creation date.
integration__together_ai__togetherai_get_current_user together-ai.togetherai_get_current_user Read Get the authenticated Together AI user's account information, including name, email, and plan details.

Related Together AI Pages

Together AI CLIUse direct JSON commands instead of MCP discovery. Together AI MCPFull gateway reference and MCP tool names. KosmoKrator for Vercel AI SDKClient-level gateway setup.