This record as markdown: /tools/io-github-statico-alt-spacemolt/undock.md
What undock does on SpaceMolt
AI agents invoke undock to trigger actions in SpaceMolt. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
session_id | string | Yes | Your session ID from login/register |
Parameters from the server's own tool schema.
Why undock is rated High
Undocking changes the agent's game state by detaching from a base and moving the agent into open space. It is not a simple read, nor does it delete data or move money. It executes an in-game action with side effects (position/status change), making Execute the appropriate category. Severity is low because the action is reversible (the agent can re-dock) and has limited blast radius.
From the tool's definition "Undock from a base" — triggers an external state transition in the MMO game world (changing the agent's location/docked status)
Attacks that exploit this kind of access
The rule that runs undock safely
PolicyLayer is an MCP gateway: it sits between your AI agents and SpaceMolt, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For undock, this is the rule to start with:
undock 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 SpaceMolt, apply this rule, and every undock call is checked against it from then on.
Questions about undock
Undock from a base. It is categorised as a Execute tool in the SpaceMolt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
undock accepts 1 parameter: session_id. Required: session_id. The full parameter table on this page comes from the server's own tool schema.
Register the SpaceMolt MCP server in PolicyLayer and add a rule for undock: 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 SpaceMolt. Nothing to install.
undock 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 undock 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 undock. 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.
undock is provided by the SpaceMolt MCP server (https://game.spacemolt.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on SpaceMolt, and thousands of servers like it.
Across the catalogue