Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/flujo-app/mcp-sandbox-computer-vm-for-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/flujo-app/mcp-sandbox-computer-vm-for-ai/sandbox-computer-fly)<a href="https://agentmods.dev/mcp/flujo-app/mcp-sandbox-computer-vm-for-ai/sandbox-computer-fly"><img src="https://agentmods.dev/badge/mcp/flujo-app/mcp-sandbox-computer-vm-for-ai/sandbox-computer-fly/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/flujo-app/mcp-sandbox-computer-vm-for-ai/sandbox-computer-fly"><img src="https://agentmods.dev/badge/mcp/flujo-app/mcp-sandbox-computer-vm-for-ai/sandbox-computer-fly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sandbox-computer-fly scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"sandbox-computer-fly": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"mcp-sandbox-computer-vm-for-ai",
"--backend",
"fly"
],
"env": {
"ENABLE_LIFECYCLE_TOOLS": "true",
"AUTO_INSTALL_FLYCTL": "true"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 16 lines scan A 08c1f23a3db6
sandbox-computer-fly is an MCP server published in the GitHub repository flujo-app/mcp-sandbox-computer-vm-for-ai (3 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other mcp servers, from other repositories
magic
MCP server "magic" as configured in polterguy/magic. Runs in Docker (docker.io/servergardens/magic-aio:v24.1.3). Needs 1 environment variable to run.
k8s-mcp-server
MCP server "k8s-mcp-server" as configured in VersusControl/devops-ai-guidelines. Launched with ${workspaceFolder}/code/04/bin/k8s-mcp-server.
hatchdoor
MCP server "hatchdoor" as configured in BatterWorks/Hatchdoor. Runs in Docker (docker.io/battermanz/hatchdoor:2.8.1).
mcp-server-openshift
OpenShift/Kubernetes cluster management via the oc CLI for MCP clients. Runs locally from the mcp-server-openshift npm package. Needs 2 environment variables to run.
nandi-proxmox-mcp
Open source Proxmox MCP server for secure VM/CT operations. Powered by NANDI Services. Runs locally from the nandi-proxmox-mcp npm package. Needs 1 environment variable to run.
haltproof
Cryptographically auditable emergency-shutdown orchestration for Slurm, Kubernetes, and IPMI/BMC clusters. Runs locally from the haltproof-cli Python package.