gd_create_object
AI agents use gd_create_object to create or update resources in Geometry Dash Mcp Geode — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Geometry Dash Mcp Geode environment.
The tool creates new objects within Geometry Dash levels, which is a reversible write operation. It modifies the game level state but does not execute arbitrary code, delete data, or incur financial impact. Severity is medium because misuse could create many unwanted objects requiring manual cleanup, but the effects are not destructive or irreversible.
From the tool's definition Tool name 'gd_create_object' combined with server context describing 'creation...of Geometry Dash levels' indicates data creation.
Attacks that exploit this kind of access
gd_create_object. It is categorised as a Write tool in the Geometry Dash Mcp Geode MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Geometry Dash Mcp Geode MCP server in PolicyLayer and add a rule for gd_create_object: 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 Geometry Dash Mcp Geode. Nothing to install.
gd_create_object is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gd_create_object 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 gd_create_object. 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.
gd_create_object is provided by the Geometry Dash Mcp Geode MCP server (noame2289-afk/geometry-dash-mcp-geode). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →