KosmoKrator

productivity

Lambda Labs MCP Integration for Vercel AI SDK

Connect Lambda Labs 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 Lambda Labs feedback View package source

Connect Lambda Labs 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.

Lambda Labs MCP Config for Vercel AI SDK

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

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

Run the Gateway Manually

kosmokrator mcp:serve --integration=lambda-labs --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Lambda Labs 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.

Lambda Labs Tools Visible to Vercel AI SDK

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

MCP toolSource functionTypeDescription
integration__lambda_labs__lambda_labs_list_instances lambda-labs.lambda_labs_list_instances Read List all GPU instances in the Lambda Labs account. Returns instance IDs, names, status, IP addresses, and GPU configuration.
integration__lambda_labs__lambda_labs_get_instance lambda-labs.lambda_labs_get_instance Read Get details for a specific Lambda Labs GPU instance by ID. Returns full instance information including status, IP, region, and GPU type.
integration__lambda_labs__lambda_labs_launch_instance lambda-labs.lambda_labs_launch_instance Write Launch a new GPU instance on Lambda Labs. Requires a region name, instance type, SSH key IDs, and optionally a name and image.
integration__lambda_labs__lambda_labs_list_ssh_keys lambda-labs.lambda_labs_list_ssh_keys Read List all SSH keys registered in the Lambda Labs account. Returns key IDs, names, and public key fingerprints.
integration__lambda_labs__lambda_labs_list_instance_types lambda-labs.lambda_labs_list_instance_types Read List all available GPU instance types on Lambda Labs. Returns specs including GPU model, VRAM, vCPUs, memory, and pricing.
integration__lambda_labs__lambda_labs_list_images lambda-labs.lambda_labs_list_images Read List all available machine images on Lambda Labs. Returns image IDs, names, and descriptions for OS templates and custom images.
integration__lambda_labs__lambda_labs_get_current_user lambda-labs.lambda_labs_get_current_user Read Get information about the current authenticated Lambda Labs user, including email, user ID, and account status.

Related Lambda Labs Pages

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