start_multiplayer_test
Start a real local multiplayer test from PLAY MODE. Creates an explicitly private, hidden lobby when needed, validates capacity, launches 1-2 sbox.exe clients with -joinlocal, and tracks joins from the pre-spawn host-side connection baseline. Overlapping tracked runs are rejected so unrelated con...
This record as markdown: /tools/sbox/start-multiplayer-test.md
What start_multiplayer_test does on Sbox
AI agents invoke start_multiplayer_test to trigger actions in Sbox. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why start_multiplayer_test is rated High
Spawns external game engine processes with significant resource consumption and side effects; requires cleanup.
From the tool's definition launches sbox.exe clients, tracks joins, spawned PIDs
Attacks that exploit this kind of access
The rule that runs start_multiplayer_test safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sbox, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start_multiplayer_test, this is the rule to start with:
start_multiplayer_test stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Sbox, apply this rule, and every start_multiplayer_test call is checked against it from then on.
Questions about start_multiplayer_test
Start a real local multiplayer test from PLAY MODE. Creates an explicitly private, hidden lobby when needed, validates capacity, launches 1-2 sbox.exe clients with -joinlocal, and tracks joins from the pre-spawn host-side connection baseline. Overlapping tracked runs are rejected so unrelated connections cannot falsely satisfy a join wait. Each client can use about 4.5 GB RAM and take about 80 seconds to join. Returns spawned PIDs, baseline/expected connection counts, and an optional join-wait job; poll multiplayer_test_status and always finish with stop_multiplayer_test. It is categorised as a Execute tool in the Sbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sbox MCP server in PolicyLayer and add a rule for start_multiplayer_test: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sbox. Nothing to install.
start_multiplayer_test is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_multiplayer_test rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for start_multiplayer_test. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
start_multiplayer_test is provided by the Sbox MCP server (sbox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sbox, and thousands of servers like it.
This server
Across the catalogue