Run OpenAI Agents SDK Tools in a Cloud VM and Get Files Back

result = await Runner.run(agent, "Check the machine and save when you ran.")

import asyncio

from agents import Runner
from agents.testing import ScriptedModel, assistant_message, function_call

import sandbox_tools
from sandbox_tools import agent

# Stands in for the LLM: each step is one model turn.
agent.model = ScriptedModel([
    [function_call("run_shell", {"command": "uname -sr && nproc && free -h | head -2 && date -u > ran-at.txt"}, call_id="call_1")],
    [function_call("download_file", {"path": "ran-at.txt"}, call_id="call_2")],
    [assistant_message("Done. The timestamp file is in artifacts/ran-at.txt.")],
])


async def main() -> None:
    result = await Runner.run(agent, "Check the machine and save when you ran.")
    for item in result.new_items:
        if item.type == "tool_call_output_item":
            print(f"--- tool output\n{item.output}")
    print("--- final_output\n" + result.final_output)
    print("--- sandbox", sandbox_tools.sandbox.id)


asyncio.run(main())

$ python scripted_run.py
--- tool output
exit code 0
Linux 6.18.56-sandboxer
2
               total        used        free      shared  buff/cache   available
Mem:           3.8Gi       304Mi       3.1Gi       352Ki       624Mi       3.5Gi
--- tool output
saved artifacts/ran-at.txt (32 bytes)
--- final_output
Done. The timestamp file is in artifacts/ran-at.txt.
--- sandbox sb_qdxatv1dvg
OPENAI_API_KEY is not set, skipping trace export
$ cat artifacts/ran-at.txt
Tue Oct 27 02:08:36 AM UTC 2026

sbx scp sb_qdxatv1dvg:/home/user/ran-at.txt ./
sbx scp -r sb_qdxatv1dvg:/home/user/out ./
sbx delete sb_qdxatv1dvg --yes

import asyncio
import os

from agents.mcp import MCPServerStreamableHttp


async def main() -> None:
    async with MCPServerStreamableHttp(
        name="sandboxer",
        params={
            "url": "https://sandboxer.com/mcp",
            "headers": {"Authorization": f"Bearer {os.environ['SANDBOXER_API_KEY']}"},
        },
        client_session_timeout_seconds=900,   # create_sandbox and long exec calls outlast the 5 s default
    ) as sandboxer:
        tools = await sandboxer.list_tools()
        print(len(tools), "tools")
        for tool in tools:
            print(f"{tool.name:16} {(tool.description or '').split('.')[0]}")


asyncio.run(main())

$ python hosted_mcp.py
18 tools
create_sandbox   Create a cloud sandbox (an Ubuntu microVM with root, Docker, git, Node and Python) and wait until it is ready
list_sandboxes   List your sandboxes with their state, URL and labels
get_sandbox      Show one sandbox: state, URL, when it stops automatically, labels and stored bytes
exec             Run a shell command (bash -c) in the sandbox
command_status   Status of a detached command: running or its exit code, and its output
kill_command     Stop a detached command
read_file        Read a file from the sandbox (up to 5 MiB)
write_file       Create or overwrite a file in the sandbox (up to 5 MiB)
host_port        Serve a port of the sandbox on a stable public HTTPS URL
…
delete_sandbox   Delete a sandbox permanently: its disk, memory and automatic snapshots go (named snapshots saved from it stay)
save_snapshot    Save the sandbox as a named snapshot to create new sandboxes from, and wait until it is saved
list_snapshots   List your named snapshots: name, version, labels, created time, stored bytes (what counts toward your storage) and disk size (logical)
delete_snapshot  Delete one named snapshot (one version, e

from agents.mcp import create_static_tool_filter

MCPServerStreamableHttp(
    ...,
    tool_filter=create_static_tool_filter(
        allowed_tool_names=["create_sandbox", "exec", "read_file", "write_file", "stop_sandbox"]
    ),
)
# list_tools() → ['create_sandbox', 'exec', 'read_file', 'write_file', 'stop_sandbox']