Import media files (video, audio, images, PNG overlays) into the project root bin.
AI agents use import_files to create or update resources in Media-Editor-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Media-Editor-MCP environment.
This tool creates or adds new media elements to a video editing project. While imports modify the project structure and add data, they are reversible (files can be removed or projects reverted). The impact is limited to the current project's media library without affecting external systems or causing irreversible damage.
From the tool's definition Tool description states it 'Import[s] media files...into the project root bin', which involves adding new assets to the project—a reversible modification of project state.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Import media files (video, audio, images, PNG overlays) into the project root bin. It is categorised as a Write tool in the Media-Editor-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Media-Editor- MCP server in PolicyLayer and add a rule for import_files: 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 Media-Editor-MCP. Nothing to install.
import_files 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 import_files 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 import_files. 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.
import_files is provided by the Media-Editor- MCP server (nguyenph88/media-editor-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 →