selection_feather

Feather the edges of the current selection.

SERVERMcp Anything SOURCEZaymadkid/mcp-anything

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mcp-anything/selection-feather.md

WHAT IT DOES

What selection_feather does on Mcp Anything

AI agents use selection_feather to create or update resources in Mcp Anything, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Anything environment.

RISK

Why selection_feather is rated Medium

This tool modifies selection state rather than destructively removing data or executing arbitrary commands. The operation is reversible (selection can be reselected or undone). It does not read-only (it changes state), nor is it destructive (the underlying data remains intact), nor does it execute arbitrary code or trigger external side effects.

From the tool's definition Tool name 'selection_feather' describes an operation that modifies the current selection state by feathering edges. The verb 'feather' indicates a transformative operation on the active selection object.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs selection_feather safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Anything, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For selection_feather, this is the rule to start with:

selection_feather Rate-limited

selection_feather stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "selection_feather": {
      "limits": [
        {
          "counter": "selection_feather_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Anything, apply this rule, and every selection_feather call is checked against it from then on.

FAQ

Questions about selection_feather

What does the selection_feather tool do? +

Feather the edges of the current selection. It is categorised as a Write tool in the Mcp Anything MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on selection_feather? +

Register the Mcp Anything MCP server in PolicyLayer and add a rule for selection_feather: 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 Anything. Nothing to install.

What risk level is selection_feather? +

selection_feather is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit selection_feather? +

Yes. Add a rate_limit block to the selection_feather 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.

How do I block selection_feather completely? +

Set action: deny in the PolicyLayer policy for selection_feather. 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.

What MCP server provides selection_feather? +

selection_feather is provided by the Mcp Anything MCP server (Zaymadkid/mcp-anything). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Anything, and thousands of servers like it.

This server

All 261 Mcp Anything tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →