Critical Risk →

jump

Jump to an adjacent star system, or plot a numeric bearing with a Pathfinder Drive (Use get_system to see connected systems. Jump time = 7 − speed ticks (speed 1 = 6t, speed 6 = 1t). Fuel cost scales with ship mass and speed. PATHFINDER DRIVE: if target_system is a number it is read as a compass ...

Part of the SpaceMolt server.

jump can permanently delete data in SpaceMolt, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE SPACEMOLT →

Free to start. No card required.

AI agents may call jump to permanently remove or destroy resources in SpaceMolt. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.

Without a policy, an AI agent could call jump in a loop, permanently destroying resources in SpaceMolt. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "jump"
  ]
}

See the full SpaceMolt policy for all 182 tools.

Get this rule live on your own SpaceMolt server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY SPACEMOLT →

View all 182 tools →

These attack patterns abuse exactly the kind of access jump gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so jump only ever does what you allow.

SECURE SPACEMOLT →

Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the jump tool do? +

Jump to an adjacent star system, or plot a numeric bearing with a Pathfinder Drive (Use get_system to see connected systems. Jump time = 7 − speed ticks (speed 1 = 6t, speed 6 = 1t). Fuel cost scales with ship mass and speed. PATHFINDER DRIVE: if target_system is a number it is read as a compass bearing in degrees — 0 points along the +X galactic axis and the angle increases counter-clockwise toward +Y at 90, so plot bearing = degrees(atan2(destY-originY, destX-originX)) using get_map coordinates. This requires a Pathfinder Drive module and drifts off the jump network across open space: far slower than a lane jump, with a one-time fuel cost. The command returns immediately — poll get_location for live coordinates. If the heading passes close to a system you drop out there; otherwise you drift indefinitely until you change course. MID-DRIFT REDIRECT: while already on a pathfinder drift you can submit a new numeric bearing to re-plot the heading instantly from your current galactic position — no inertia, no slide. Same 5x fuel cost each time; the previous destination is forgotten and the ray-cast runs again from where you are right now. A bearing 180 degrees from your current heading sends you back the way you came (nothing was in your corridor on the way out, or you'd have dropped out there, so the reverse ray's first hit is your launch system). self_destruct remains a last-resort escape if you've run out of fuel for redirects. Getting the timing right is the hard part.). It is categorised as a Destructive tool in the SpaceMolt MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on jump? +

Register the SpaceMolt MCP server in PolicyLayer and add a rule for jump: 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.

What risk level is jump? +

jump is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit jump? +

Yes. Add a rate_limit block to the jump 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.

How do I block jump completely? +

Set action: deny in the PolicyLayer policy for jump. 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.

What MCP server provides jump? +

jump 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.

Enforce policy on every SpaceMolt tool call.

Deterministic rules across all 182 SpaceMolt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.