Add margin.
AI agents use vfx_margin to create or update resources in vidMagik-mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your vidMagik-mcp environment.
Adding a margin to a video is a reversible video composition operation that modifies the visual output without permanently destroying or deleting data. It creates or modifies frames (Write category) rather than executing arbitrary code (Execute) or irreversibly destroying content (Destructive).
From the tool's definition Tool name 'vfx_margin' and description 'Add margin' indicate a reversible modification to video content. The prefix 'vfx_' (visual effects) and the operation 'Add margin' align with non-destructive video composition/formatting operations typical of MoviePy…
Attacks that exploit this kind of access
Add margin. It is categorised as a Write tool in the vidMagik-mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the vidMagik- MCP server in PolicyLayer and add a rule for vfx_margin: 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 vidMagik-mcp. Nothing to install.
vfx_margin 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 vfx_margin 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 vfx_margin. 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.
vfx_margin is provided by the vidMagik- MCP server (vizionik25/vidmagik-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 →