Agentsandboxes

io.github.pooriaarabPublished by GitHub account pooriaarabv1.0.0Updated Oct 26, 2026

A neutral index of cloud sandboxes for AI agents.

The publisher's own server: AI Benchmark Index

VerifiedStreamable HTTPWeb executableCloud & Infrastructure AI & ML

Server details

Identifier: io.github.pooriaarab/agentsandboxes
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Oct 21, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account pooriaarab for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.pooriaarab%2Fagentsandboxes.svg)](https://sourceweft.com/mcp/io.github.pooriaarab%2Fagentsandboxes?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A read-only index of cloud sandboxes for AI agents, letting an assistant search providers by text, place and category and inspect listings and data sources.

What you can do: Search published sandbox providers by text, place and category
Fetch a single provider listing by its slug
Browse the countries, regions and cities that have providers
List categories with their provider counts
Read index statistics and the last data change time
List the data sources behind the listings, with license and refresh details
When to use it: Useful when you need to find or compare cloud sandbox providers for running AI agents, or want to check where such listing data comes from before relying on it.
Requirements: A remote streamable HTTP endpoint; no packages, environment variables or headers are declared, and no authentication is declared.

Before you install

The data is a third-party index of providers, so listings may be incomplete or out of date; check the listed sources and refresh details before depending on them. All tools appear read-only.

Installation

In SourceWeft

Open Agentsandboxes in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.pooriaarab%2Fagentsandboxes/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentsandboxes": {
      "type": "http",
      "url": "https://agentsandboxes.fyi/mcp"
    }
  }
}

README

This repository has no README.

Tools

search_listings

Search published sandbox providers by text, place and category.

Parametersqcitysortlimitcursorregioncountrycategory

get_listing

Get one published sandbox provider by its slug.

Parametersslugrequired

list_places

List countries, regions and cities that have sandbox providers.

Takes no parameters.

get_stats

Get the number of published sandbox providers, places and categories, and when the data last changed.

Takes no parameters.

list_sources

List where the sandbox provider data comes from, with the license and refresh of each source.

Takes no parameters.

Version history

v1.0.0LatestOct 21, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.

Other Aibenchmarkindex integrations

AI Benchmark Index

com.aibenchmarkindexOfficial publisher

Remote MCP endpoint for the AI Benchmark Index that lets an assistant search published AI benchmarks by text, place and category, and read their sources.

Streamable HTTPWeb executable

AI & ML6 toolsOct 26, 2026