Remove background in the input image using Recraft.\n
AI agents use remove_background to create or update resources in Mcp Recraft Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Recraft Server environment.
This tool modifies an image by removing its background. It produces a new output image (transformed version), which is a reversible write/transformation operation — the original image is not necessarily destroyed, and the result is a new artifact. It does not execute code, delete data irreversibly in a destructive sense, or involve finances.
From the tool's definition Remove background in the input image using Recraft
Attacks that exploit this kind of access
Remove background in the input image using Recraft.\n. It is categorised as a Write tool in the Mcp Recraft Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Recraft Server MCP server in PolicyLayer and add a rule for remove_background: 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 Recraft Server. Nothing to install.
remove_background 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 remove_background 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 remove_background. 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.
remove_background is provided by the Mcp Recraft Server MCP server (@recraft-ai/mcp-recraft-server). 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 →