Make dimensions even.
AI agents use vfx_even_size 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.
The tool modifies video dimensions to even numbers, which is a common preprocessing step in video editing. This falls under Write (creates or modifies data reversibly) rather than Read (no modification) or Execute (no arbitrary code execution). Severity is medium because dimension changes could affect downstream processing or output quality, but the operation is reversible and non-destructive.
From the tool's definition Tool name 'vfx_even_size' and description 'Make dimensions even' indicate modification of video/image dimensions. This is a reversible transformation that alters video metadata/properties but does not delete or execute arbitrary code.
Attacks that exploit this kind of access
Make dimensions even. 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_even_size: 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_even_size 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_even_size 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_even_size. 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_even_size 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 →