Agentsandboxes is answering right now. Last checked 14 min ago. It exposes 11 tools.
A neutral index of cloud sandboxes for AI agents.
Today is the operative word: we check Agentsandboxes every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add agentsandboxes --transport http https://agentsandboxes.fyi/mcp
https://agentsandboxes.fyi/mcp
[mcp_servers.agentsandboxes]
url = "https://agentsandboxes.fyi/mcp"
{
"mcpServers": {
"agentsandboxes": {
"url": "https://agentsandboxes.fyi/mcp"
}
}
}
{
"servers": {
"agentsandboxes": {
"type": "http",
"url": "https://agentsandboxes.fyi/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_product
list_product_categories
list_categories
get_course
list_courses
get_listing
search_listings
list_places
list_products
list_sources
get_stats
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentsandboxes.fyi/mcp | streamable-http | answering | 1747 ms | 14 min ago |
A neutral index of cloud sandboxes for AI agents.
Secure Linux sandboxes for AI agents, as MCP tools.
Linux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.
Clean, normalized SEC EDGAR / FRED / ETF / index data for AI agents.
Create and manage secure sandboxes for running AI agent code
Sandboxes, storage, secrets, queues, timers, locks, inboxes and run ledger for AI bots. One MCP.
Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows
Curated index of B2B offerings for AI agents: fit, non-fit, limits, sourced claims.
Answers built from our own checks of this server.