INDIVIDUAL MCP TOOL

cp_destroy

Permanently destroy a service and release its resources.

computeportal.ionone authenticationAvailability not checked

LIVE ENDPOINT

https://mcp.computeportal.io/mcp

No auth detected

Connect to this endpoint to inspect the live schema for cp_destroy and invoke it with your own arguments.

{}

Potential side effects detected · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.computeportal]
url = "https://mcp.computeportal.io/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "computeportal": {
      "type": "http",
      "url": "https://mcp.computeportal.io/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: computeportal
Remote MCP URL: https://mcp.computeportal.io/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "computeportal": {
      "url": "https://mcp.computeportal.io/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "computeportal": {
      "type": "http",
      "url": "https://mcp.computeportal.io/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "computeportal",
  "transport": "streamable-http",
  "url": "https://mcp.computeportal.io/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

cp_deploy — Deploy a service to Compute Portal from a Docker image or a public GitHub repo.
cp_service_list — List all running services on Compute Portal.
cp_service_status — Get the current status, replica count, and health of a service.
cp_service_logs — Fetch the most recent log lines from a running service.
cp_scale — Scale a service's replica count or update its CPU/memory resource limits.
cp_gpu_list — List available GPU nodes with specs, utilization, VRAM usage, and temperature.
cp_gpu_reserve — Reserve GPU capacity for a fixed duration.
cp_gpu_run — Submit a one-shot GPU job (billed per second, returns job ID and initial status).