DevOps

computeportal.io

Deploys and manages services on Compute Portal, including listing services, checking status and logs, and scaling replicas or resource limits.

1 endpoint21 known toolsFirst detected October 4, 2026Last detected October 4, 2026

ENDPOINT 1

https://mcp.computeportal.io/mcp

No auth detected

MCP server metadata

Name: computeportal
Version: 0.1.0

Capabilities

tools.listChanged

Known tools 21

cp_deploy

Deploy a service to Compute Portal from a Docker image or a public GitHub repo.

Inferred read-only

cp_service_list

List all running services on Compute Portal.

Inferred read-only

cp_service_status

Get the current status, replica count, and health of a service.

Inferred read-only

cp_service_logs

Fetch the most recent log lines from a running service.

Inferred read-only

cp_scale

Scale a service's replica count or update its CPU/memory resource limits.

Potential side effects

cp_destroy

Permanently destroy a service and release its resources.

Potential side effects

cp_gpu_list

List available GPU nodes with specs, utilization, VRAM usage, and temperature.

Inferred read-only

cp_gpu_reserve

Reserve GPU capacity for a fixed duration.

Inferred read-only

cp_gpu_run

Submit a one-shot GPU job (billed per second, returns job ID and initial status).

Inferred read-only

cp_node_list

List all CP bare-metal nodes with hardware specs and reservation status.

Inferred read-only

cp_env_set

Set one or more environment variables on a running service.

Inferred read-only

cp_billing_balance

Return the current account balance, credit, burn rate, and alert threshold.

Inferred read-only

cp_billing_usage

Return itemized billing usage for a given period.

Inferred read-only

cp_region_list

List all Compute Portal regions with compliance certifications, GPU availability, and latency.

Inferred read-only

cp_db_create

Provision a managed database (postgres, redis, mysql, or mongo).

Inferred read-only

cp_sandbox_create

Spin up an isolated GPU-attached microVM sandbox for executing AI agent code.

Inferred read-only

cp_sandbox_exec

Execute a command inside a running sandbox and return stdout, stderr, exit code, and duration.

Potential side effects

cp_sandbox_destroy

Destroy a sandbox and release its GPU resources.

Potential side effects

cp_domain_add

Attach a custom hostname to a CP service.

Inferred read-only

cp_domain_list

List all domains (default and custom) attached to a service.

Inferred read-only

cp_domain_remove

Remove a custom hostname from a CP service.

Potential side effects

CONNECT WITH APPROVAL

Client installation

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.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for computeportal.io was fetched 2026-10-21T11:49:19.464Z.

Trust status Trusted

computeportal.io is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.