Inspect a Meshy task; optionally download the .glb on success.
AI agents call get_meshy_task_status to retrieve information from Meshy Youtube without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the status of a task and conditionally downloads an artifact (a .glb 3D model file). Both operations are non-destructive read actions with no side effects on the underlying system. Downloading a file for inspection/use is a read operation. The blast radius of misuse is minimal—an attacker could inspect task statuses or download models, but cannot modify, delete, or execute arbitrary code.
From the tool's definition Tool name 'get_meshy_task_status' and description 'Inspect a Meshy task; optionally download the .glb on success' indicate retrieval and querying of task status information.
Attacks that exploit this kind of access
Inspect a Meshy task; optionally download the .glb on success. It is categorised as a Read tool in the Meshy Youtube MCP Server, which means it retrieves data without modifying state.
Register the Meshy Youtube MCP server in PolicyLayer and add a rule for get_meshy_task_status: 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 Meshy Youtube. Nothing to install.
get_meshy_task_status 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 get_meshy_task_status 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 get_meshy_task_status. 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.
get_meshy_task_status is provided by the Meshy Youtube MCP server (scottcjn/meshy-youtube-mcp). 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 →