virtual_try_on
Apply virtual clothing try-on to a person image using AI. Upload a person image and up to 5 clothing items to see how they would look wearing those clothes. Supports both single and multiple clothing combinations for complete outfit visualization.
This record as markdown: /tools/199-mcp-mcp-kling/virtual-try-on.md
What virtual_try_on does on MCP Kling
AI agents invoke virtual_try_on to trigger actions in MCP Kling. 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.
Why virtual_try_on is rated High
This tool triggers an external AI operation that processes uploaded images and generates a new composite image. It runs an AI inference pipeline on external servers — this is an Execute-level action (triggering external computation with side effects), not a simple Write since it doesn't just store data, and not a simple Read since it produces a new AI-generated output.
From the tool's definition 'Apply virtual clothing try-on to a person image using AI. Upload a person image and up to 5 clothing items to see how they would look wearing those clothes.'
Attacks that exploit this kind of access
The rule that runs virtual_try_on safely
PolicyLayer is an MCP gateway: it sits between your AI agents and MCP Kling, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For virtual_try_on, this is the rule to start with:
virtual_try_on stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect MCP Kling, apply this rule, and every virtual_try_on call is checked against it from then on.
Questions about virtual_try_on
Apply virtual clothing try-on to a person image using AI. Upload a person image and up to 5 clothing items to see how they would look wearing those clothes. Supports both single and multiple clothing combinations for complete outfit visualization. It is categorised as a Execute tool in the MCP Kling MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Kling MCP server in PolicyLayer and add a rule for virtual_try_on: 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 MCP Kling. Nothing to install.
virtual_try_on 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 virtual_try_on 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 virtual_try_on. 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.
virtual_try_on is provided by the MCP Kling MCP server (199-mcp/mcp-kling). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on MCP Kling, and thousands of servers like it.
Across the catalogue