AI agents invoke aseprite_cli to trigger actions in Aseprite. 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.
The tool executes arbitrary CLI commands in Aseprite's native interface, which can trigger complex operations including file I/O, script execution, and visual transformations.
From the tool's definition Tool description states 'Run raw Aseprite CLI arguments' and 'any native capability not covered by a higher-level tool.' This provides direct execution of arbitrary Aseprite CLI commands without constraints.
Attacks that exploit this kind of access
Run raw Aseprite CLI arguments. Use for any native capability not covered by a higher-level tool. It is categorised as a Execute tool in the Aseprite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Aseprite MCP server in PolicyLayer and add a rule for aseprite_cli: 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 Aseprite. Nothing to install.
aseprite_cli 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 aseprite_cli 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 aseprite_cli. 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.
aseprite_cli is provided by the Aseprite MCP server (ryan3719/asprite-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 →