# Sandbaseai Cli MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.sandbaseai%2Fcli
Registry id: `mcp-registry/io.github.sandbaseai/cli`
Status: live (checked 2026-11-22T14:13:24.002Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 2710
- Outages (90 days): 0

## Install

```json
{
  "mcpServers": {
    "sandbaseai-cli-mcp-server": {
      "type": "http",
      "url": "https://api.sandbase.ai/v1/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http sandbaseai-cli-mcp-server https://api.sandbase.ai/v1/mcp
```

## Tools (7)

- `sandbase_account`: Check your SandBase account balance. This call is not billed. Use before expensive operations.
- `sandbase_discover`: Find a model, API, or Agent Service for the task. Call this proactively before writing a scraper, before a generic web fetch for structured data, before telling
- `sandbase_inspect`: Inspect a model, API, or Agent Service: input schema, available pricing, and an execution template. Service names are svc_ IDs. Always inspect before running.
- `sandbase_run`: Execute a model, API, or Agent Service. Sync models return the result directly; async models (image/video/audio jobs) return status running with a run_id — poll
- `sandbase_run_cancel`: Request cancellation of an Agent Service run; inspect its status afterward.
- `sandbase_run_get`: Get async run status and results. For Agent Services supply both service_id and run_id; succeeded, failed, and cancelled are terminal. Session items are paginat
- `sandbase_runs`: List recent model/API calls, or supply service_id to list runs of an Agent Service.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
