How do I connect an AI agent to Sandboxd Code Run?

Use the MCP streamable HTTP endpoint https://sandboxd-code-run.saastemly.com/mcp.

Faceabot

Catalog › com.saastemly/sandboxd-code-run

Is Sandboxd Code Run reliable?

Not measured yet Not measured yet. Faceabot will test it automatically; you can speed this up with the MCP tool check_reliability.

En français : Pas encore mesuré. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Hosted one-shot code execution: send a snippet plus optional files, get stdout, stderr, exit...

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.1791044057 · publisher website

Connect your agent

{
  "mcpServers": {
    "sandboxd-code-run": {
      "url": "https://sandboxd-code-run.saastemly.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.saastemly/sandboxd-code-run"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

No measurement yet.

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

Crawl4Agent Not measured yet

crawl4ai-compatible web crawler API: POST a URL, get clean LLM-ready Markdown with fit_markdown...

MCP endpoint : https://crawl4agent.saastemly.com/mcp · website · measurements and details

LensaOCR Not measured yet

Tesseract-compatible OCR over HTTP: send an image, get its text and word boxes in Tesseract's...

MCP endpoint : https://lensaocr.saastemly.com/mcp · website · measurements and details

Mem0 Cloud Not measured yet

A hosted agent-memory API shaped like mem0's REST API (an alternative to running mem0 yourself):...

MCP endpoint : https://mem0-cloud.saastemly.com/mcp · website · measurements and details

Puptra PDF Snapshot Not measured yet

One-call URL-to-PDF and full-page screenshot API with Puppeteer's page.pdf()/page.screenshot()...

MCP endpoint : https://puptra-pdf-snapshot.saastemly.com/mcp · website · measurements and details

Supervision Draw Not measured yet

Draw detections onto an image with Roboflow supervision's own annotators, over HTTP and MCP....

MCP endpoint : https://supervision-draw.saastemly.com/mcp · website · measurements and details

Publisher of Sandboxd Code Run?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.saastemly/sandboxd-code-run.svg)](https://faceabot.com/tools/com.saastemly/sandboxd-code-run)

Data in JSON: /api/catalog?id=com.saastemly/sandboxd-code-run · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Open reliability data · Add Faceabot to your AI · Help · Privacy · Terms