Run a read-only script in After Effects
AI agents invoke run-script to trigger actions in After Effects MCP Server. 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.
Scripts in After Effects, even if constrained to read-only operations, are code execution primitives that can query system state, access file systems, and invoke After Effects APIs whose full impact may not be visible.
From the tool's definition Tool name is 'run-script' and description states it runs 'a script in After Effects'. Even though marked 'read-only', executing arbitrary scripts in After Effects can trigger external operations, access system resources, and produce side effects depending on…
Attacks that exploit this kind of access
Run a read-only script in After Effects. It is categorised as a Execute tool in the After Effects MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the After Effects MCP Server MCP server in PolicyLayer and add a rule for run-script: 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 After Effects MCP Server. Nothing to install.
run-script 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 run-script 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 run-script. 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.
run-script is provided by the After Effects MCP Server MCP server (rtx1025189518-source/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 →