List all objects in the current level (first 50 objects)
AI agents call gd_list_objects to retrieve information from Geometry Dash Mcp Geode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data about objects in a Geometry Dash level without creating, modifying, deleting, or executing any operations. It is a simple read operation with minimal risk—an AI agent cannot cause harm by listing objects. Severity is low because the blast radius is confined to information disclosure of level composition.
From the tool's definition Tool name 'gd_list_objects' and description 'List all objects in the current level' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all objects in the current level (first 50 objects). It is categorised as a Read tool in the Geometry Dash Mcp Geode MCP Server, which means it retrieves data without modifying state.
Register the Geometry Dash Mcp Geode MCP server in PolicyLayer and add a rule for gd_list_objects: 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_list_objects is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gd_list_objects 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_list_objects. 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_list_objects 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 →